Adaptive/Assistive Technology
Event TypePoster
P/V Maybe
Arts & Design
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
1. Learning From Human-Robot Interactions in Modeled Scenes
Contributors
Mark Murnane
Max Breitmeyer
Cynthia Matuszek
Francis Ferraro
Don Engel
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
New Technologies
Research & Education
Adaptive Technology
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
By combining virtual reality with existing robotics simulators, we have created a tool for simulating and testing a wide range of human robot interactions, particularly to assist in grounded language acquisition.
By combining virtual reality with existing robotics simulators, we have created a tool for simulating and testing a wide range of human robot interactions, particularly to assist in grounded language acquisition.
Contributors
Mark Murnane
University of Maryland, Baltimore County
Max Breitmeyer
University of Maryland, Baltimore County
Cynthia Matuszek
University of Maryland, Baltimore County
Francis Ferraro
University of Maryland, Baltimore County
Don Engel
University of Maryland, Baltimore County
2. MagniFinger: Fingertip-Mounted Microscope for Augmenting Human Perception
Contributors
Noriyasu Obushi
Sohei Wakisaka
Shunichi Kasahara
Atsushi Hiyama
Masahiko Inami
Event Type
Poster
P/V Maybe
Arts & Design
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
MagniFinger is a fingertip-worn microscopy device that augments the limited abilities of human visual and tactile sensory systems in micrometer-scale environments. MagniFinger makes use of the finger's dexterous motor skills to achieve precise and intuitive control while allowing the user to observe the desired position simply by placing a fingertip. Vibration-based tactile feedback is displayed based on the luminance of a magnified image, providing the user with the feeling of touching the magnified world.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
MagniFinger is a fingertip-worn microscopy device that augments the limited abilities of human visual and tactile sensory systems in micrometer-scale environments. MagniFinger makes use of the finger's dexterous motor skills to achieve precise and intuitive control while allowing the user to observe the desired position simply by placing a fingertip. Vibration-based tactile feedback is displayed based on the luminance of a magnified image, providing the user with the feeling of touching the magnified world.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Contributors
Noriyasu Obushi
The University of Tokyo
Sohei Wakisaka
The University of Tokyo
Shunichi Kasahara
The University of Tokyo
Sony Computer Science Laboratories, Inc.
Atsushi Hiyama
The University of Tokyo
RIKEN Center for Advanced Intelligence Project
Masahiko Inami
The University of Tokyo
3. Massively Parallel High Quality Layout Generation
Contributors
Vineet Batra
Ankit Phogat
Tarun Beri
Event Type
Poster
P/V No
P/V Maybe
Arts & Design
New Technologies
Research & Education
Adaptive Technology
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We present a first true SIMD formulation for graphic layout design by employing a CUDA-enabled GPU to generate millions of possible design permutations and rank them on aesthetic appeal using weighted parameters like symmetry, alignment, density, balance, etc. Our method generates high-quality results for multiple page sizes in real time and enables authors to accelerate design velocity.
We present a first true SIMD formulation for graphic layout design by employing a CUDA-enabled GPU to generate millions of possible design permutations and rank them on aesthetic appeal using weighted parameters like symmetry, alignment, density, balance, etc. Our method generates high-quality results for multiple page sizes in real time and enables authors to accelerate design velocity.
Contributors
Vineet Batra
Adobe
Ankit Phogat
Adobe
Tarun Beri
Adobe
4. Partial Zoom on Small Display for People Suffering From Presbyopia
Contributors
Huiyi Fang
Kenji Funahashi
Shinji Mizuno
Yuji Iwahori
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
New Technologies
Research & Education
Adaptive Technology
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
A partial zoom-in method for presbyopic people is proposed. The area of a user's attention is zoomed in to read clearly, and the magnification rate of the area around it is gradually reduced to zoom-out rate so that all information is displayed in the small display. Our idea is applied to an actual document containing text and image, i.e. a PDF file and a web page, and our method is implemented on a tablet PC to develop an experimental system. Presbyopic people tried it to see how it works, and they evaluated it positively.
A partial zoom-in method for presbyopic people is proposed. The area of a user's attention is zoomed in to read clearly, and the magnification rate of the area around it is gradually reduced to zoom-out rate so that all information is displayed in the small display. Our idea is applied to an actual document containing text and image, i.e. a PDF file and a web page, and our method is implemented on a tablet PC to develop an experimental system. Presbyopic people tried it to see how it works, and they evaluated it positively.
Contributors
Huiyi Fang
Nagoya Institute of Technology
Kenji Funahashi
Nagoya Institute of Technology
Shinji Mizuno
Aichi Institute of Technology
Yuji Iwahori
Chubu University
5. Rapid 3D Building Modeling by Sketching
Contributors
Chia-Yu Chen
I-Chen Lin
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
New Technologies
Research & Education
Adaptive Technology
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
This poster proposes an intuitive tool for creating 3D architectural models, where a user only needs to sketch the outline of a frontal or oblique view of a building.
This poster proposes an intuitive tool for creating 3D architectural models, where a user only needs to sketch the outline of a frontal or oblique view of a building.
Contributors
Chia-Yu Chen
National Chiao Tung University
I-Chen Lin
National Chiao Tung University
6. Scented Graphics: Exploration in Inkjet Scented-Printing
Contributors
Yi-Ching Kang
Hiroki Nishino
Event Type
Poster
P/V Maybe
Arts & Design
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
“Scented Graphics” is our artistic experiment with a scented-printing technique that utilizes an inkjet printer. Mixing water-soluble aromatic oils with inks, an inkjet printer is utilized to control scent mixing with high precision at almost no extra cost. We mimicked Swiss graphic design in our experiment to facilitate preliminary investigation of this technique. As scent mixing is a fundamental technique in olfactory art, our experiments can be beneficial as design exemplars as a preliminary exploration of the technique.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
“Scented Graphics” is our artistic experiment with a scented-printing technique that utilizes an inkjet printer. Mixing water-soluble aromatic oils with inks, an inkjet printer is utilized to control scent mixing with high precision at almost no extra cost. We mimicked Swiss graphic design in our experiment to facilitate preliminary investigation of this technique. As scent mixing is a fundamental technique in olfactory art, our experiments can be beneficial as design exemplars as a preliminary exploration of the technique.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Contributors
Yi-Ching Kang
Chang Gung University
Hiroki Nishino
Chang Gung University
7. Virtual Reality Mirror Therapy Rehabilitation For Post-Stroke Patients
Contributors
Levan Sulimanov
Marc Olano
Event Type
Poster
P/V Maybe
Arts & Design
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
The traditional mirror therapy currently provided for post-stroke patients was redeveloped in virtual reality. VR Mirror Therapy provides a new set of exercises and environmental settings: patients can do hand-cross movements, use an unlimited number of therapeutic resources for exercises, undergo such therapy from home, and be surrounded by a customizable virtual environment.
The traditional mirror therapy currently provided for post-stroke patients was redeveloped in virtual reality. VR Mirror Therapy provides a new set of exercises and environmental settings: patients can do hand-cross movements, use an unlimited number of therapeutic resources for exercises, undergo such therapy from home, and be surrounded by a customizable virtual environment.
Contributors
Levan Sulimanov
University of Maryland, Baltimore County (UMBC)
Marc Olano
University of Maryland, Baltimore County (UMBC)
Art & Design
Event TypePoster
P/V Maybe
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
8. A Formal Process to Design Visual Archetypes Based on Character Taxonomies
SessionArt & Design
Contributors
Angela Wang
Anthony Dalton Eason
Ergun Akleman
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
In this work, we present a formal process to construct visual designs for character archetypes that are given by "verbal descriptions." This process is based on visual semiotics that are used for creating clear meaning behind design choices while still retaining a sense of aesthetic through principles of artistic design. Using this process, we have developed a set of encyclopedic references for a wide variety of psychology and literary archetypes to demonstrate the power of this approach. We also used this process successfully in a visual storytelling class.
In this work, we present a formal process to construct visual designs for character archetypes that are given by "verbal descriptions." This process is based on visual semiotics that are used for creating clear meaning behind design choices while still retaining a sense of aesthetic through principles of artistic design. Using this process, we have developed a set of encyclopedic references for a wide variety of psychology and literary archetypes to demonstrate the power of this approach. We also used this process successfully in a visual storytelling class.
Contributors
Angela Wang
Texas A&M University
Texas A&M University
Anthony Dalton Eason
Texas A&M University
Texas A&M University
Ergun Akleman
Texas A&M University
Texas A&M University
9. Automatic Layout Generation for Graphical Design Magazines
SessionArt & Design
Contributors
Sou Tabata
Hiroki Yoshihara
Haruka Maeda
Kei Yokoyama
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
The proposed system automatically generates layouts for graphical design magazines. In this system, when images, texts, and the number of pages are input, an appropriate layout is automatically generated in consideration of design. This is performed by a randomized generation of a large number of candidates in accordance with a rule set of minimum conditions that must be satisfied for the layouts. The candidates are evaluated by a learning-to-rank estimator, and top scores are returned to the user. This enables users to greatly improve the efficiency of layout creation/editing.
The proposed system automatically generates layouts for graphical design magazines. In this system, when images, texts, and the number of pages are input, an appropriate layout is automatically generated in consideration of design. This is performed by a randomized generation of a large number of candidates in accordance with a rule set of minimum conditions that must be satisfied for the layouts. The candidates are evaluated by a learning-to-rank estimator, and top scores are returned to the user. This enables users to greatly improve the efficiency of layout creation/editing.
Contributors
Sou Tabata
Dai Nippon Printing Co., Ltd
Hiroki Yoshihara
Dai Nippon Printing Co., Ltd
Haruka Maeda
Dai Nippon Printing Co., Ltd
Kei Yokoyama
A+U Publishing Co., Ltd.
10. Exploring Color Variations for Vector Graphics
SessionArt & Design
Contributors
Sayan Ghosh
Jose Echevarria
Vineet Batra
Ankit Phogat
Event Type
Poster
P/V No
P/V Maybe
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We propose a novel and intuitive method for exploring recoloring variations of vector graphics. Our method tries to infer some of them before formulating color transfer as a transport problem between the weighted color distributions of the reference and the target vector graphics. We enable creative exploration by providing fine-grain control over the resulting transfer, allowing users to modify relative color distributions in real time.
We propose a novel and intuitive method for exploring recoloring variations of vector graphics. Our method tries to infer some of them before formulating color transfer as a transport problem between the weighted color distributions of the reference and the target vector graphics. We enable creative exploration by providing fine-grain control over the resulting transfer, allowing users to modify relative color distributions in real time.
Contributors
Sayan Ghosh
Adobe
Jose Echevarria
Adobe
Vineet Batra
Adobe
Ankit Phogat
Adobe
11. Fully Automatic Colorization for Anime Character Considering Accurate Eye Colors
SessionArt & Design
Contributors
Kenta Akita
Yuki Morimoto
Reiji Tsuruno
Event Type
Poster
P/V No
P/V Maybe
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
In this paper, we propose a method to colorize line drawings of anime characters’ faces with colors from a reference image. Previous studies using reference images often fail to realize fully-automatic colorization, especially for small areas, e.g., eye colors in the resulting image may differ from the reference image. The proposed method accurately colorizes eyes in the input line drawing using automatically-computed hints. The hints are round patches used to specify the positions and corresponding colors extracted from the eye areas of a reference image.
In this paper, we propose a method to colorize line drawings of anime characters’ faces with colors from a reference image. Previous studies using reference images often fail to realize fully-automatic colorization, especially for small areas, e.g., eye colors in the resulting image may differ from the reference image. The proposed method accurately colorizes eyes in the input line drawing using automatically-computed hints. The hints are round patches used to specify the positions and corresponding colors extracted from the eye areas of a reference image.
Contributors
Kenta Akita
Kyushu University
Yuki Morimoto
Kyushu University
Reiji Tsuruno
Kyushu University
12. Glove Puppetry Cloud Theater Through a Virtual Reality Network
SessionArt & Design
Contributors
DER-LOR WAY
Weng-Kei Lau
Tzu Ying Huang
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
Gaming & Interactive
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
This paper presents a collaborative work in a multi-user virtual reality system for puppetry’s opera. A grand-master's puppet show performance could be recorded in our system. Without any professional training, users can play a glove puppetry performance by their hand in our cloud theater. The cloud theater of glove puppetry, targeted at interactive virtual reality, experiences the understanding of culture. Our research not only delivers a balance of art and technology in culture creativity, but it also preserves folk art.
This paper presents a collaborative work in a multi-user virtual reality system for puppetry’s opera. A grand-master's puppet show performance could be recorded in our system. Without any professional training, users can play a glove puppetry performance by their hand in our cloud theater. The cloud theater of glove puppetry, targeted at interactive virtual reality, experiences the understanding of culture. Our research not only delivers a balance of art and technology in culture creativity, but it also preserves folk art.
Contributors
DER-LOR WAY
Taipei National University of the Arts
Weng-Kei Lau
Taipei National University of the Arts
Tzu Ying Huang
Taipei National University of the Arts
13. Graph Matching Based Anime Colorization With Multiple References
SessionArt & Design
Contributors
Akinobu Maejima
Hiroyuki Kubo
Takuya Funatomi
Tatsuo Yotsukura
Satoshi Nakamura
Yasuhiro Mukaigawa
Event Type
Poster
P/V No
P/V Maybe
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We propose a graph-matching based anime-colorization method from line-drawing sketches using multiple references. We design the cost function of a graph-matching problem so that it exhibits the performance of final colorization result. An optimal reference can be selected according to the score derived from the cost function for each frame of the input sequence. Thanks to the multiple reference images, our method can colorize a target line drawing even if the graph structure drastically changed from character animation. We demonstrate our method's effectiveness using images from our anime production.
We propose a graph-matching based anime-colorization method from line-drawing sketches using multiple references. We design the cost function of a graph-matching problem so that it exhibits the performance of final colorization result. An optimal reference can be selected according to the score derived from the cost function for each frame of the input sequence. Thanks to the multiple reference images, our method can colorize a target line drawing even if the graph structure drastically changed from character animation. We demonstrate our method's effectiveness using images from our anime production.
Contributors
Akinobu Maejima
OLM Digital Inc.
IMAGICA GROUP Inc.
Hiroyuki Kubo
NAIST
Takuya Funatomi
NAIST
Tatsuo Yotsukura
OLM Digital Inc.
IMAGICA GROUP Inc.
Satoshi Nakamura
NAIST
Yasuhiro Mukaigawa
NAIST
14. Interactive Spatial Augmented Reality for Chinese Opera
SessionArt & Design
Contributors
Yanxiang Zhang
YiRun Shen
WeiWei Zhang
ZiQiang Zhu
PengFei Ma
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
Gaming & Interactive
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
The authors designed an interactive spatial augmented reality system for Chinese Opera stage performance based on the technologies of UWB positioning and Bluetooth® triggering. The actor's position is obtained through the antenna tag carried by the actor and the signal-base station placed on stage. Special effects can be triggered through the Bluetooth® module according to the actor. The system has a higher degree of freedom in practical applications, which can present an interactive spatial augmented reality effect and provide new possibilities for the application of spatial augmented reality in the stage performance.
The authors designed an interactive spatial augmented reality system for Chinese Opera stage performance based on the technologies of UWB positioning and Bluetooth® triggering. The actor's position is obtained through the antenna tag carried by the actor and the signal-base station placed on stage. Special effects can be triggered through the Bluetooth® module according to the actor. The system has a higher degree of freedom in practical applications, which can present an interactive spatial augmented reality effect and provide new possibilities for the application of spatial augmented reality in the stage performance.
Contributors
Yanxiang Zhang
University of Science and Technology of China
Department of Communication of Science and Technology
YiRun Shen
University of Science and Technology of China
Department of Communication of Science and Technology
WeiWei Zhang
University of Science and Technology of China
Department of Communication of Science and Technology
ZiQiang Zhu
University of Science and Technology of China
Department of Communication of Science and Technology
PengFei Ma
University of Science and Technology of China
Department of Communication of Science and Technology
15. Interactive Virtual Reality Orchestral Music
SessionArt & Design
Contributors
Yanxiang Zhang
Li Tao
YiRun Shen
Elieisar Clayton
Fangbemi Abassin
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
The authors developed a VR orchestral application for interactive music experience. It allows virtual music instruments in orchestral to be repositioned spatially, dynamically, and interactively in VR space, while environments are changed, thus presenting a restructured traditional orchestral with 3D audio technology into a new music art form.
The authors developed a VR orchestral application for interactive music experience. It allows virtual music instruments in orchestral to be repositioned spatially, dynamically, and interactively in VR space, while environments are changed, thus presenting a restructured traditional orchestral with 3D audio technology into a new music art form.
Contributors
Yanxiang Zhang
University of Science and Technology of China
Department of Communication of Science and Technology
Li Tao
University of Science and Technology of China
Department of Communication of Science and Technology
YiRun Shen
University of Science and Technology of China
Department of Communication of Science and Technology
Elieisar Clayton
University of Science and Technology of China
Department of Communication of Science and Technology
Fangbemi Abassin
University of Science and Technology of China
Department of Communication of Science and Technology
16. ISSv2 and OpenISS Distributed System for Real-Time Interaction for Performing Arts
SessionArt & Design
Contributors
Serguei Mokhov
Deschanel Li
Haotao Lai
Jashanjot Singh
Yiran Shen
Jonathan Llewellyn
Miao Song
Sudhir Mudur
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
The OpenISS poised to be ISSv2's core is a distributed system for real-time projection mapping, which allows people to view the applied projection effects remotely.
The OpenISS poised to be ISSv2's core is a distributed system for real-time projection mapping, which allows people to view the applied projection effects remotely.
Contributors
Serguei Mokhov
Concordia University
mDreams Pictures, Inc; CCIFF.ca
Deschanel Li
University of Ottawa
Haotao Lai
Concordia University
Jashanjot Singh
Concordia University
Yiran Shen
Concordia University
Jonathan Llewellyn
Concordia University
Miao Song
Concordia University
Sudhir Mudur
Concordia University
17. Layered Reconstruction of Stippling Art
SessionArt & Design
Contributors
Amal Dev Parakkat
Pooran Memari
Marie-Paule Cani
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
In this work, we introduce a dedicated variant of traditional 2D reconstruction in which the input point set (a stippled image) can include different regions corresponding to different point densities. Our method converts this input into a layered, vector representation, which includes a main shape plus internal, closed regions defined by their boundary.
In this work, we introduce a dedicated variant of traditional 2D reconstruction in which the input point set (a stippled image) can include different regions corresponding to different point densities. Our method converts this input into a layered, vector representation, which includes a main shape plus internal, closed regions defined by their boundary.
Contributors
Amal Dev Parakkat
LIX, Ecole Polytechnique CNRS
Pooran Memari
LIX, Ecole Polytechnique CNRS
Marie-Paule Cani
LIX, Ecole Polytechnique CNRS
18. Meet in Rain: A Serious Game to Help the Better Appreciation of Chinese Poems
SessionArt & Design
Contributors
Ye-Ning Jiang
Hiroki Nishino
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
Meet in Rain is a serious game on Chinese poetry. While invoking various events, players must complete tasks, which help them better appreciate the poems by exploring imaginary sceneries that depict Chinese poems. Its visual design also mimics Chinese paintings in the era the poems were created. As only a few serious games exist for Chinese poetry, and they mostly focus on knowledge acquisition, our work provides a rare design exemplar of a serious game that is designed with the intention of fostering aesthetic appreciation for a cultural subject.
Meet in Rain is a serious game on Chinese poetry. While invoking various events, players must complete tasks, which help them better appreciate the poems by exploring imaginary sceneries that depict Chinese poems. Its visual design also mimics Chinese paintings in the era the poems were created. As only a few serious games exist for Chinese poetry, and they mostly focus on knowledge acquisition, our work provides a rare design exemplar of a serious game that is designed with the intention of fostering aesthetic appreciation for a cultural subject.
Contributors
Ye-Ning Jiang
Chang Gung University
Hiroki Nishino
Chang Gung University
19. Multi-Task Audio-Driven Facial Animation
SessionArt & Design
Contributors
Youngsoo Kim
Shounan An
Youngbak Jo
Seungje Park
Shindong Kang
Insoo Oh
Duke Donghyun Kim
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We propose MulTaNet, a deep neural network to solve the multi-task audio-driven facial animation problem in an end-to-end fashion. Extensive experiments indicate that MulTaNet generates more natural-looking and stable facial animation, while showing better generalization capacity for unseen languages compared to previous approaches.
We propose MulTaNet, a deep neural network to solve the multi-task audio-driven facial animation problem in an end-to-end fashion. Extensive experiments indicate that MulTaNet generates more natural-looking and stable facial animation, while showing better generalization capacity for unseen languages compared to previous approaches.
Contributors
Youngsoo Kim
Netmarble
Shounan An
Netmarble
Youngbak Jo
Netmarble
Seungje Park
Netmarble
Shindong Kang
Netmarble
Insoo Oh
Netmarble
Duke Donghyun Kim
Netmarble
20. Pieces of the Past, Maya Treasure Hunt: A Virtual Reality Game Experience
SessionArt & Design
Contributor
Jiawei Huang
Event Type
Poster
P/V Maybe
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We created an educational game in an archaeological context with scientifically-constructed and georeferenced 3D models using structure from motion (SfM) mapping, in combination with models created from archaeological findings.
We created an educational game in an archaeological context with scientifically-constructed and georeferenced 3D models using structure from motion (SfM) mapping, in combination with models created from archaeological findings.
Contributor
Jiawei Huang
Pennsylvania State University
21. Vector Based Glyph Style Transfer
SessionArt & Design
Contributors
Praveen Kumar Dhanuka
Nirmal Kumawat
Nipun Jindal
Event Type
Poster
P/V Maybe
P/V Yes
Arts & Design
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
A style transfer system transfers a modification of a modified vector-based glyph to one or more additional vector-based glyphs. This includes identifying similar segments of the additional glyph based on a style transfer policy, which defines conditions for transferring the modification to the additional glyph.
A style transfer system transfers a modification of a modified vector-based glyph to one or more additional vector-based glyphs. This includes identifying similar segments of the additional glyph based on a style transfer policy, which defines conditions for transferring the modification to the additional glyph.
Contributors
Praveen Kumar Dhanuka
Adobe Inc.
Georgie Tech
Nirmal Kumawat
Adobe Inc.
Nipun Jindal
Adobe Inc.
Augmented & Virtual Realities
Event TypePoster
P/V Yes
New Technologies
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
22. 3D Printing for Mixed Reality Hands-On Museum Exhibit Interaction
Contributors
Laura Mann
Oleg Fryazinov
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
3D printing and mixed reality are combined to bring a new level of interactivity to museum exhibitions. A pipeline achieving an experience for visitors to be hands-on with realistic 3D-printed replicas of artefacts, which are then digitally augmented to have the genuine artefacts’ appearances, preserving the originals are presented.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
3D printing and mixed reality are combined to bring a new level of interactivity to museum exhibitions. A pipeline achieving an experience for visitors to be hands-on with realistic 3D-printed replicas of artefacts, which are then digitally augmented to have the genuine artefacts’ appearances, preserving the originals are presented.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Contributors
Laura Mann
NCCA, Bournemouth University
Oleg Fryazinov
NCCA, Bournemouth University
23. A Method for Rectifying Inclination of Panoramic Images
Contributor
Naoki Kawai
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We propose a method for transforming inclined panoramic images into the right posture, as they ware captured straight, using neither additional information nor external instructions.
We propose a method for transforming inclined panoramic images into the right posture, as they ware captured straight, using neither additional information nor external instructions.
Contributor
Naoki Kawai
Dai Nippon Printing Co., Ltd.
24. An Intuitive and Educational Programming Tool With Tangible Blocks and AR
Contributors
Keisuke Hattori
Tatsunori Hirai
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
Elementary schools around the world are increasingly teaching programming. When teaching beginners programming, they use robots, puzzles, and visual programming to make learning easy to understand. We created a tool using tangible blocks in AR. This makes it possible to intuitively learn programming without any limitations. It is possible to create a program with intuitive interaction with reality. Teachers who teach programming to children evaluated the merits and demerits of using this tool at school.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Elementary schools around the world are increasingly teaching programming. When teaching beginners programming, they use robots, puzzles, and visual programming to make learning easy to understand. We created a tool using tangible blocks in AR. This makes it possible to intuitively learn programming without any limitations. It is possible to create a program with intuitive interaction with reality. Teachers who teach programming to children evaluated the merits and demerits of using this tool at school.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Contributors
Keisuke Hattori
Komazawa University
Tatsunori Hirai
Komazawa University
25. Biodigital: Transform Data to Experience, Beyond Data Visualization
Contributors
Takahito Ito
Cesar A. Hidalgo
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We focus on how to tell stories and aim to provide more engaging or efficient ways to learn from data. The concept "Data to Experiences" is sublimating data into virtual reality experiences beyond data visualization. The first prototype called "VR DATA EXPERIENCE" was released in 2016. We developed this concept to VR story telling, "Biodigital," in 2018. "Biodigital" is a Sci-Fi interactive story set in the year 2117. A journey through technology advancements takes you to 2117 when human minds are cloned and start growing beyond human consciousness.
We focus on how to tell stories and aim to provide more engaging or efficient ways to learn from data. The concept "Data to Experiences" is sublimating data into virtual reality experiences beyond data visualization. The first prototype called "VR DATA EXPERIENCE" was released in 2016. We developed this concept to VR story telling, "Biodigital," in 2018. "Biodigital" is a Sci-Fi interactive story set in the year 2117. A journey through technology advancements takes you to 2117 when human minds are cloned and start growing beyond human consciousness.
Contributors
Takahito Ito
NHK (Japan Broadcasting Corporation)
Collective Learning group at the MIT Media Lab
Cesar A. Hidalgo
Collective Learning Group at the MIT Media Lab
26. Deep-ChildAR Bot: Educational Activities and Safety Care Augmented Reality System With Deep-Learning for Preschool
Contributors
YoonJung Park
Hyocheol Ro
Tack-Don Han
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We propose a projection-based augmented reality robot system that provides pervasive support for the education and safety of preschoolers via a deep learning framework. This system utilizes real-world objects as metaphors for educational tools by performing real-time object detection based on deep learning, and it recognizes dangers of real-world objects that may pose risks to children. We designed the system in a simple and intuitive way to provide user-friendly interfaces and interactions for children. Children's experiences through the proposed system can improve their physical, cognitive, emotional, and thinking abilities.
We propose a projection-based augmented reality robot system that provides pervasive support for the education and safety of preschoolers via a deep learning framework. This system utilizes real-world objects as metaphors for educational tools by performing real-time object detection based on deep learning, and it recognizes dangers of real-world objects that may pose risks to children. We designed the system in a simple and intuitive way to provide user-friendly interfaces and interactions for children. Children's experiences through the proposed system can improve their physical, cognitive, emotional, and thinking abilities.
Contributors
YoonJung Park
Yonsei University
Media System Lab
Hyocheol Ro
Yonsei university
Tack-Don Han
Yonsei University
27. Flood Action VR: A Virtual Reality Framework for Disaster Awareness and Emergency Response Training
Contributors
Yusuf Sermet
Ibrahim Demir
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
This paper presents a virtual reality framework that creates a realistic 3D gaming environment with real-time and historical weather and disaster conditions. The main goal of the project is to increase public awareness about disasters by using gamification techniques and train and evaluate emergency responders by simulating real-life scenarios. The system is supported by voice recognition to interact with the virtual world and analyze user’s actions and voice to detect emotional and psychological state.
This paper presents a virtual reality framework that creates a realistic 3D gaming environment with real-time and historical weather and disaster conditions. The main goal of the project is to increase public awareness about disasters by using gamification techniques and train and evaluate emergency responders by simulating real-life scenarios. The system is supported by voice recognition to interact with the virtual world and analyze user’s actions and voice to detect emotional and psychological state.
Contributors
Yusuf Sermet
University of Iowa
Ibrahim Demir
University of Iowa
28. HeroMirror Interactive: A Gesture Controlled Augmented Reality Gaming Experience
Contributors
Tamás Matuszka
Ferenc Czuczor
Zoltán Sóstai
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
Appropriately chosen user interfaces are essential parts of immersive augmented reality experiences. Regular user interfaces cannot be efficiently used for interactive, real-time augmented reality applications. In this study, a gesture-controlled educational gaming experience is described, where gesture recognition relies on deep learning methods. Our implementation is able to replace a depth-camera based gesture recognition system using a conventional camera while ensuring the same level of recognition accuracy.
Appropriately chosen user interfaces are essential parts of immersive augmented reality experiences. Regular user interfaces cannot be efficiently used for interactive, real-time augmented reality applications. In this study, a gesture-controlled educational gaming experience is described, where gesture recognition relies on deep learning methods. Our implementation is able to replace a depth-camera based gesture recognition system using a conventional camera while ensuring the same level of recognition accuracy.
Contributors
Tamás Matuszka
Vyu
INDE R&D
Ferenc Czuczor
INDE R&D
Zoltán Sóstai
INDE R&D
29. InNervate Immersion: Case Study of Dynamic Simulations in AR/VR Environments for Learning Muscular Innervation
Contributors
Margaret E. Cook
Amber Ackley
Karla Chang Gonzalez
Austin Payne
Jinsil Hwaryoung Seo
Caleb Kicklighter
Michelle Pine
Timothy McLaughlin
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
InNervate AR and InNervate VR are dynamic anatomy education applications which push the boundaries of existing static user interfaces and explore the relationship between the nerves of the body and movement.
InNervate AR and InNervate VR are dynamic anatomy education applications which push the boundaries of existing static user interfaces and explore the relationship between the nerves of the body and movement.
Contributors
Margaret E. Cook
Texas A&M University
Amber Ackley
Texas A&M University
Karla Chang Gonzalez
Texas A&M University
Austin Payne
Texas A&M University
Jinsil Hwaryoung Seo
Texas A&M University
Caleb Kicklighter
Texas A&M University
Michelle Pine
Texas A&M University
Timothy McLaughlin
Texas A&M University
30. Vox-Cells: Voxel-Based Visualization of Volume Data for Enhanced Understanding and Exploration in Virtual Reality (VR)
Contributors
Rowan Hughes
Campbell Strong
John McGhee
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We present Vox-Cells, a volume visualization framework designed for real-time volume investigation and exploration. We seek to treat data as a first-class citizen with a 1:1 relationship between the data and its corresponding representation. CPU-GPU transfer is minimized, and novel approaches to volume construction and lighting are explored in order to maximize performance for deployment on consumer-grade virtual reality head-mounted displays (HMD).
We present Vox-Cells, a volume visualization framework designed for real-time volume investigation and exploration. We seek to treat data as a first-class citizen with a 1:1 relationship between the data and its corresponding representation. CPU-GPU transfer is minimized, and novel approaches to volume construction and lighting are explored in order to maximize performance for deployment on consumer-grade virtual reality head-mounted displays (HMD).
Contributors
Rowan Hughes
UNSW Sydney
Campbell Strong
UNSW Sydney
John McGhee
UNSW Sydney
31. VRProp-Net: Real-Time Interaction With Virtual Props
Contributors
Catherine Taylor
Robin McNicholas
Darren Cosker
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We present a novel approach for transporting physical objects into virtual environments to be used as interactive props, which control the behavior of elements in the virtual scene. In this pipeline, we design VRProp-Net, a convolutional neural network for predicting rigid and non-rigid deformations from unlabeled RGB images.
We present a novel approach for transporting physical objects into virtual environments to be used as interactive props, which control the behavior of elements in the virtual scene. In this pipeline, we design VRProp-Net, a convolutional neural network for predicting rigid and non-rigid deformations from unlabeled RGB images.
Contributors
Catherine Taylor
University of Bath
Marshmallow Laser Feast
Robin McNicholas
Marshmallow Laser Feast
Darren Cosker
University of Bath
Display & Rendering
Event TypePoster
P/V Maybe
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
32. 3D Aerial Display With Micro Mirror Array Plate and Reversed Depth Integral Photography
SessionDisplay & Rendering
Contributors
Nahomi Maki
Toshiaki Yamanouchi
Kazuhisa Yanaka
Event Type
Poster
P/V Maybe
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We propose a new aerial imaging display in which autostereoscopic objects with horizontal and vertical parallax appear as if they are floating in the air. This system operates by displaying an integral photography image in which depth is reversed beforehand and by observing the image from the other side of a micromirror array.
We propose a new aerial imaging display in which autostereoscopic objects with horizontal and vertical parallax appear as if they are floating in the air. This system operates by displaying an integral photography image in which depth is reversed beforehand and by observing the image from the other side of a micromirror array.
Contributors
Nahomi Maki
Tokyo University of the Arts
Toshiaki Yamanouchi
Kanagawa Institute of Technology
Kazuhisa Yanaka
Kanagawa Institute of Technology
33. A Data-Driven Compression Method For Transient Rendering
SessionDisplay & Rendering
Contributors
Yun Liang
Mingqin Chen
Zesheng Huang
Diego Gutierrez
Adolfo Muñoz
Julio Marco
Event Type
Poster
P/V Maybe
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We present a data-driven compression method for transient light transport, based on encoder-decoder deep neural networks, that reduces the size of transient renders by a factor of 32 while significantly mitigating variance.
We present a data-driven compression method for transient light transport, based on encoder-decoder deep neural networks, that reduces the size of transient renders by a factor of 32 while significantly mitigating variance.
Contributors
Yun Liang
South China Agricultural University
Mingqin Chen
South China Agricultural University
Zesheng Huang
South China Agricultural University
Diego Gutierrez
Universidad de Zaragoza, I3A
Adolfo Muñoz
Universidad de Zaragoza, I3A
Julio Marco
Universidad de Zaragoza, I3A
34. A Null-Scattering Path Integral Formulation of Light Transport
SessionDisplay & Rendering
Contributors
Bailey Miller
Iliyan Georgiev
Wojciech Jarosz
Event Type
Poster
P/V Maybe
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We enable unbiased, multiple importance sampling in heterogeneous media through a path integral formulation of the null radiative transfer equation.
We enable unbiased, multiple importance sampling in heterogeneous media through a path integral formulation of the null radiative transfer equation.
Contributors
Bailey Miller
Dartmouth College
Iliyan Georgiev
Autodesk
Wojciech Jarosz
Dartmouth College
36. DiCE: Dichoptic Contrast Enhancement for VR and Stereo Displays
SessionDisplay & Rendering
Contributors
Fangcheng Zhong
George Koulieris
George Drettakis
Fredo Durand
Martin Banks
Mathieu Chambe
Rafal Mantiuk
Event Type
Poster
P/V Maybe
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
A novel technique that takes advantage of binocular fusion to boost perceived local contrast and visual quality of images.
A novel technique that takes advantage of binocular fusion to boost perceived local contrast and visual quality of images.
Contributors
Fangcheng Zhong
University of Cambridge
George Koulieris
Durham University
George Drettakis
Université Côte d'Azur, Inria
Fredo Durand
Massachusetts Institute of Technology
Martin Banks
University of California-Berkeley
Mathieu Chambe
Univ Rennes
Rafal Mantiuk
University of Cambridge
37. Distortion-Free Wide-Angle Portraits on Camera Phones
SessionDisplay & Rendering
Contributors
YiChang Shih
Wei-Sheng Lai
Chia-Kai Liang
Event Type
Poster
P/V Maybe
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
Photographers take wide-angle shots to enjoy expanding views and group portraits that never miss anyone. In spite of the rapid proliferation of wide-angle cameras on mobile phones, a wider field-of-view (FOV) introduces a stronger perspective distortion. Most notably, faces are stretched, squished, and skewed, to look vastly different from real-life. Correcting such distortions requires professional editing skills, as trivial manipulations can introduce other kinds of distortions. This poster introduces a new algorithm to undistort faces without affecting other parts of the photo.
Photographers take wide-angle shots to enjoy expanding views and group portraits that never miss anyone. In spite of the rapid proliferation of wide-angle cameras on mobile phones, a wider field-of-view (FOV) introduces a stronger perspective distortion. Most notably, faces are stretched, squished, and skewed, to look vastly different from real-life. Correcting such distortions requires professional editing skills, as trivial manipulations can introduce other kinds of distortions. This poster introduces a new algorithm to undistort faces without affecting other parts of the photo.
Contributors
YiChang Shih
Google
Wei-Sheng Lai
Google
Chia-Kai Liang
Google
38. Ellipsoidal Path Connections for Time-Gated Rendering
SessionDisplay & Rendering
Contributors
Adithya Pediredla
Ashok Veeraraghavan
Ioannis Gkioulekas
Event Type
Poster
P/V Maybe
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We develop a path-sampling procedure for the efficient, unbiased Monte Carlo rendering of time-gated cameras. Applications include lidar sensing, imaging through scattering, and non-line-of-sight imaging.
We develop a path-sampling procedure for the efficient, unbiased Monte Carlo rendering of time-gated cameras. Applications include lidar sensing, imaging through scattering, and non-line-of-sight imaging.
Contributors
Adithya Pediredla
Rice University
Carnegie Mellon University
Ashok Veeraraghavan
Rice University
Ioannis Gkioulekas
Carnegie Mellon University
39. Exploration of Using Face Tracking to Reduce GPU Rendering on Current and Future Auto-Stereoscopic Displays
SessionDisplay & Rendering
Contributors
Xingyu Pan
Mengya Zheng
Abraham Campbell
Event Type
Poster
P/V Maybe
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
A technique that reduces GPU consumption when using auto-stereoscopic displays by giving the display a context awareness of its observers is presented. This technique can be applied to reduce future GPU requirements for auto-stereoscopic displays in the future.
A technique that reduces GPU consumption when using auto-stereoscopic displays by giving the display a context awareness of its observers is presented. This technique can be applied to reduce future GPU requirements for auto-stereoscopic displays in the future.
Contributors
Xingyu Pan
University College Dublin
Mengya Zheng
University College Dublin
Abraham Campbell
University College Dublin
40. Geometry-Aware Scattering Compensation for 3D Printing
SessionDisplay & Rendering
Contributors
Denis Sumin
Tobias Rittig
Vahid Babaei
Thomas Nindel
Alexander Wilkie
Piotr Didyk
Bernd Bickel
Jaroslav Krivanek
Karol Myszkowski
Tim Weyrich
Event Type
Poster
P/V Maybe
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We present a pipeline for high-fidelity, full-color 3D printing that compensates for sub-surface scattering in printing materials within arbitrarily shaped objects. We demonstrate superior quality in texture and color reproduction.
We present a pipeline for high-fidelity, full-color 3D printing that compensates for sub-surface scattering in printing materials within arbitrarily shaped objects. We demonstrate superior quality in texture and color reproduction.
Contributors
Denis Sumin
Max-Planck-Institute for Informatics
Tobias Rittig
Charles University in Prague
Vahid Babaei
Max Planck Institute for Informatics
Thomas Nindel
Charles University in Prague
Alexander Wilkie
Charles University in Prague
Piotr Didyk
Università della Svizzera italiana
Bernd Bickel
IST Austria
Jaroslav Krivanek
Charles University in Prague
Karol Myszkowski
Max Planck Institute for Informatics
Tim Weyrich
University College London
41. GPGPU Acceleration of Environmental and Movement Datasets
SessionDisplay & Rendering
Contributors
Daniel Bird
Stephen Laycock
Event Type
Poster
P/V Maybe
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
The vast sizes of datasets produced for movement ecology require either small study areas or significant computation time for visualization. The toolkit presented here loads tag data and updates the 25 million point MODIS temperature dataset in 2.59 milliseconds on a NVidia Titan Xp, allowing large-scale visualization with environmental data.
The vast sizes of datasets produced for movement ecology require either small study areas or significant computation time for visualization. The toolkit presented here loads tag data and updates the 25 million point MODIS temperature dataset in 2.59 milliseconds on a NVidia Titan Xp, allowing large-scale visualization with environmental data.
Contributors
Daniel Bird
University of East Anglia
Stephen Laycock
University of East Anglia
42. Handheld Super-Resolution
SessionDisplay & Rendering
Contributors
Ignacio Garcia Dorado
Bartlomiej Wronski
Manfred Ernst
Damien Kelly
Michael Krainin
Chia-Kai Liang
Marc Levoy
Peyman Milanfar
Event Type
Poster
P/V Maybe
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
A multi-frame super-resolution algorithm that supplants demosaicing in a camera pipeline is presented. Our method creates an RGB image from a burst of raw (Bayer) images by exploiting the sub-pixel displacements arising from (natural) hand tremor present in handheld photography. We demonstrate artifact free results using a novel adaptive kernel method based on a robust alignment error rejection model.
A multi-frame super-resolution algorithm that supplants demosaicing in a camera pipeline is presented. Our method creates an RGB image from a burst of raw (Bayer) images by exploiting the sub-pixel displacements arising from (natural) hand tremor present in handheld photography. We demonstrate artifact free results using a novel adaptive kernel method based on a robust alignment error rejection model.
Contributors
Ignacio Garcia Dorado
Google Research
Bartlomiej Wronski
Google Research
Manfred Ernst
Google Research
Damien Kelly
Google Research
Michael Krainin
Google Research
Chia-Kai Liang
Google Research
Marc Levoy
Google Research
Peyman Milanfar
Google Research
43. IR Surface Reflectance Estimation and Material Type Recognition Using Two-Stream Net and Kinect Camera
SessionDisplay & Rendering
Contributors
Seokyeong Lee
Hwasup Lim
Sangchul Ahn
Seungkyu Lee
Event Type
Poster
P/V Maybe
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
Material-type recognition using color or light field camera has been studied and collect diverse visual characteristics of each material type. However, visual pattern-based approaches for material-type recognition without direct acquisition of surface reflectance show limited performance. We propose IR surface reflectance estimation using an off-the-shelf ToF (Time-of-flight) active sensor, such as Kinect, and perform surface material-type recognition based on both color and reflectance clues. Two stream deep neural networks consist of convolutional neural network encoding visual clues, and recurrent neural network encoding reflectance characteristic is proposed for material classification.
Material-type recognition using color or light field camera has been studied and collect diverse visual characteristics of each material type. However, visual pattern-based approaches for material-type recognition without direct acquisition of surface reflectance show limited performance. We propose IR surface reflectance estimation using an off-the-shelf ToF (Time-of-flight) active sensor, such as Kinect, and perform surface material-type recognition based on both color and reflectance clues. Two stream deep neural networks consist of convolutional neural network encoding visual clues, and recurrent neural network encoding reflectance characteristic is proposed for material classification.
Contributors
Seokyeong Lee
Kyunghee University
Hwasup Lim
KIST
Sangchul Ahn
KIST
Seungkyu Lee
Kyunghee University
44. Optimal Multiple Importance Sampling
SessionDisplay & Rendering
Contributors
Ivo Kondapaneni
Petr Vevoda
Pascal Grittmann
Tomáš Skřivan
Philipp Slusallek
Jaroslav Křivánek
Event Type
Poster
P/V Maybe
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
The poster presents the optimal weighting functions for Multiple Importance Sampling. It shows that the variance bounds of the commonly used balance heuristic do not generally hold and the optimal weights can perform much better. It also shows that the optimal weights are equivalent to the optimal control variate.
The poster presents the optimal weighting functions for Multiple Importance Sampling. It shows that the variance bounds of the commonly used balance heuristic do not generally hold and the optimal weights can perform much better. It also shows that the optimal weights are equivalent to the optimal control variate.
Contributors
Ivo Kondapaneni
Charles University, Prague
Petr Vevoda
Charles University, Prague
Chaos Czech a.s.
Pascal Grittmann
Saarland University, Saarbrücken
Tomáš Skřivan
Institute of Science and Technology Austria
Philipp Slusallek
German Research Center for Artificial Intelligence
Saarland University, Saarbrücken
Jaroslav Křivánek
Charles University, Prague
Chaos Czech a.s.
45. Photon: A Modular, Research-Oriented Rendering System
SessionDisplay & Rendering
Contributors
Tzu-Chieh Chang
Ming Ouhyoung
Event Type
Poster
P/V Maybe
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
An open-source and cross-platform rendering system, that is designed with modularity and research in mind, is proposed. It provides a set of building blocks to facilitate the implementation of new rendering algorithms, as well as a unified foundation for comparing the performance of different methods.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
An open-source and cross-platform rendering system, that is designed with modularity and research in mind, is proposed. It provides a set of building blocks to facilitate the implementation of new rendering algorithms, as well as a unified foundation for comparing the performance of different methods.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Contributors
Tzu-Chieh Chang
National Taiwan University
Ming Ouhyoung
National Taiwan University
46. Photon Surfaces for Robust, Unbiased Volumetric Density Estimation
SessionDisplay & Rendering
Contributors
Xi Deng
Shaojie Jiao
Benedikt Bitterli
Wojciech Jarosz
Event Type
Poster
P/V Maybe
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We improve the efficiency of volume rendering by generalizing photon planes to photon surfaces, a new family of unbiased volumetric density estimators that we combine using multiple importance sampling.
We improve the efficiency of volume rendering by generalizing photon planes to photon surfaces, a new family of unbiased volumetric density estimators that we combine using multiple importance sampling.
Contributors
Xi Deng
Cornell University
Shaojie Jiao
Dartmouth College
Benedikt Bitterli
Dartmouth College
Wojciech Jarosz
Dartmouth College
47. Practical Measurement and Modeling of Spectral Skin Reflectance
SessionDisplay & Rendering
Contributors
Yuliya Gitlina
Daljit Singh Dhillon
Giuseppe Claudio Guarnera
Abhijeet Ghosh
Event Type
Poster
P/V No
P/V Maybe
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We propose a practical spectral model of skin reflectance that has sufficient complexity to match photographs under various illumination spectra, as well as a practical measurement approach for driving the model that is suitable for facial appearance capture of live subjects. Compared to previous work in computer graphics, we demonstrate higher quality estimates of spectral parameters for faces with our approach.
We propose a practical spectral model of skin reflectance that has sufficient complexity to match photographs under various illumination spectra, as well as a practical measurement approach for driving the model that is suitable for facial appearance capture of live subjects. Compared to previous work in computer graphics, we demonstrate higher quality estimates of spectral parameters for faces with our approach.
Contributors
Yuliya Gitlina
Imperial College London
Daljit Singh Dhillon
Clemson University
Giuseppe Claudio Guarnera
Norwegian University of Science and Technology
Abhijeet Ghosh
Imperial College London
Imperial College London
48. Puppeteered Rain: Interactive Illusion of Levitating Water Drops by Position-Dependent Strobe Projection
SessionDisplay & Rendering
Contributors
Shingo Kagami
Kotone Higuchi
Koichi Hashimoto
Event Type
Poster
P/V Maybe
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
Strobe light causes optical illusion, by which water drops appear to be still or to slowly move. Instead of using a single strobe light, we demonstrate the use of a high-frame-rate projector, such that rise and fall motions of water drops can be interactively controlled in a position-dependent manner.
Strobe light causes optical illusion, by which water drops appear to be still or to slowly move. Instead of using a single strobe light, we demonstrate the use of a high-frame-rate projector, such that rise and fall motions of water drops can be interactively controlled in a position-dependent manner.
Contributors
Shingo Kagami
Tohoku University
Kotone Higuchi
Tohoku University
Koichi Hashimoto
Tohoku University
49. Single Image Portrait Relighting
SessionDisplay & Rendering
Contributors
Tiancheng Sun
Jonathan T. Barron
Yun-Ta Tsai
Zexiang Xu
Xueming Yu
Graham Fyffe
Christoph Rhemann
Jay Busch
Paul Debevec
Ravi Ramamoorthi
Event Type
Poster
P/V Maybe
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We present a learning-based portrait-relighting system that can change the lighting condition of a portrait taken under an unconstrained environment to any provided environmental lighting.
We present a learning-based portrait-relighting system that can change the lighting condition of a portrait taken under an unconstrained environment to any provided environmental lighting.
Contributors
Tiancheng Sun
University of California, San Diego
Jonathan T. Barron
Google Research
Yun-Ta Tsai
Google Research
Zexiang Xu
University of California, San Diego
Xueming Yu
Google
Graham Fyffe
Google
Christoph Rhemann
Google
Jay Busch
Google
Paul Debevec
Google
Ravi Ramamoorthi
University of California, San Diego
50. Temporal and Spatial Anti-Aliasing for Rendering Reflection on a Water Surface
SessionDisplay & Rendering
Contributors
Namo Podee
Nelson Max
Kei Iwasaki
Yoshinori Dobashi
Event Type
Poster
P/V Maybe
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
A reflection of a bright light source on a dynamic surface like water surface can be difficult to render in high-quality in real-time due to reflection aliasing and flickering. In this paper, we propose a solution to this problem by approximating the reflection distribution of any aliasing-prone water surface as a Gaussian distribution. Then, we analytically integrate the reflection contribution throughout the rendering interval time. Our method is able to render in real-time a reflection of a spherical light source on highly-dynamic waves with less aliasing and unnatural flickering.
A reflection of a bright light source on a dynamic surface like water surface can be difficult to render in high-quality in real-time due to reflection aliasing and flickering. In this paper, we propose a solution to this problem by approximating the reflection distribution of any aliasing-prone water surface as a Gaussian distribution. Then, we analytically integrate the reflection contribution throughout the rendering interval time. Our method is able to render in real-time a reflection of a spherical light source on highly-dynamic waves with less aliasing and unnatural flickering.
Contributors
Namo Podee
Hokkaido University
Nelson Max
University of California, Davis
Kei Iwasaki
Wakayama University
Yoshinori Dobashi
Hokkaido University
51. Visualization of Ultra-Thin Semi-Transparent Metallic Films by Wave Simulations and Ray-Tracing Rendering
SessionDisplay & Rendering
Contributors
Wei Sen Loi
Kenneth Chau
Event Type
Poster
P/V Maybe
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
Achieving desired structural coloration using nanostructures requires bottom-up design in which the electromagnetic properties of nanostructures are simulated and then extrapolated to model their visual appearance. Computer graphics technology can be used to provide visualization of the optical properties of nanostructures on large scales. We propose to use finite-difference time-domain (FDTD) simulation to model electromagnetic interaction of visible light with nanostructures and create physical-based material models to visualize their appearance by ray-tracing rendering.
Achieving desired structural coloration using nanostructures requires bottom-up design in which the electromagnetic properties of nanostructures are simulated and then extrapolated to model their visual appearance. Computer graphics technology can be used to provide visualization of the optical properties of nanostructures on large scales. We propose to use finite-difference time-domain (FDTD) simulation to model electromagnetic interaction of visible light with nanostructures and create physical-based material models to visualize their appearance by ray-tracing rendering.
Contributors
Wei Sen Loi
University of British Columbia
Universiti Teknikal Malaysia Melaka
Kenneth Chau
The University of British Columbia
Hardware Interfaces
Event TypePoster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
52. Arque: Artificial Biomimicry-Inspired Tail for Extending Innate Body Functions
SessionHardware Interfaces
Contributors
Junichi Nabeshima
MHD Yamen Saraiji
Kouta Minamizawa
Event Type
Poster
P/V Yes
New Technologies
Research & Education
Adaptive Technology
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
For most vertebrate animals, tail plays an important role for their body, providing variant functions to enhance their mobility. Arque proposes an artificial biomimicry-inspired anthropomorphic tail, allowing us to alter our body momentum. The internal structure of the tail is driven by four artificial muscles providing the actuation mechanism. We highlight its applications as a normal tail providing active momentum alteration for balancing situations or as a full-body haptic feedback device.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
For most vertebrate animals, tail plays an important role for their body, providing variant functions to enhance their mobility. Arque proposes an artificial biomimicry-inspired anthropomorphic tail, allowing us to alter our body momentum. The internal structure of the tail is driven by four artificial muscles providing the actuation mechanism. We highlight its applications as a normal tail providing active momentum alteration for balancing situations or as a full-body haptic feedback device.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Contributors
Junichi Nabeshima
Keio University Graduate School of Media Design
MHD Yamen Saraiji
Keio Univesity Graduate School of Media Design
Kouta Minamizawa
Keio Univesity Graduate School of Media Design
53. CubeHarmonic: A New Musical Instrument Based on Rubik’s Cube With Embedded Motion Sensor
SessionHardware Interfaces
Contributors
Maria Mannone
Eri Kitamura
Jiawei Huang
Ryo Sugawara
Pascal Chiu
Yoshifumi Kitamura
Event Type
Poster
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
The fascination of geometry, the ingenuity of Rubik's cube, a musical kaleidoscope, a cutting-edge motion tracking technology: they can all be joined to create a novel musical interface, the CubeHarmonic. We present the idea and realization of this new instrument, and we discuss its possible applications and potential.
The fascination of geometry, the ingenuity of Rubik's cube, a musical kaleidoscope, a cutting-edge motion tracking technology: they can all be joined to create a novel musical interface, the CubeHarmonic. We present the idea and realization of this new instrument, and we discuss its possible applications and potential.
Contributors
Maria Mannone
University of Palermo
Eri Kitamura
Faculty of Design & Computer Sciences, Kyushu University
Jiawei Huang
Research Institute of Electrical Communication, Tohoku University
Ryo Sugawara
Research Institute of Electrical Communication, Tohoku University
Pascal Chiu
Research Institute of Electrical Communication, Tohoku University
INSA de Lyon
Yoshifumi Kitamura
Research Institute of Electrical Communication, Tohoku University
54. Designing a Full-Body Customizable Haptic Interface Using Two-Dimensional Signal Transmission
SessionHardware Interfaces
Contributors
Taichi Furukawa
Nobuhisa Hanamitsu
Yoichi Kamiyama
Hideaki Nii
Charalampos Krekoukiotis
Kouta Minamizawa
Akihito Noda
Junko Yamada
Keiichi Kitamura
Daisuke Niwa
Yoshiaki Hirano
Tetsuya Mizuguchi
Event Type
Poster
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
This full-body, customizable, haptic clothing interface aims to enhance the spatial computing experience. It not only looks as flexible as ordinary cloth, but the attached modules can also render variations of haptic feedback to all limbs of the body. It can be freely attached on textile, enabling users to customize the experience to their own liking by using two-dimensional signal transmission technology.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
This full-body, customizable, haptic clothing interface aims to enhance the spatial computing experience. It not only looks as flexible as ordinary cloth, but the attached modules can also render variations of haptic feedback to all limbs of the body. It can be freely attached on textile, enabling users to customize the experience to their own liking by using two-dimensional signal transmission technology.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Contributors
Taichi Furukawa
Keio University Graduate School of Media Design
Nobuhisa Hanamitsu
Enhance, Inc.
Keio University Graduate School of Media Design
Yoichi Kamiyama
Keio University Graduate School of Media Design
Hideaki Nii
VIVITA Japan Inc.
Charalampos Krekoukiotis
Keio University Graduate School of Media Design
Kouta Minamizawa
Keio University Graduate School of Media Design
Japan Science and Technology Agency
Akihito Noda
Nanzan University
Japan Science and Technology Agency
Junko Yamada
Teijin Limited
Keiichi Kitamura
Teijin Limited
Daisuke Niwa
Teijin Limited
Yoshiaki Hirano
Teijin Limited
Tetsuya Mizuguchi
Enhance, Inc.
Keio University Graduate School of Media Design
55. Display Methods of Projection Augmented Reality Based on Deep Learning Pose Estimation
SessionHardware Interfaces
Contributors
Hyocheol Ro
YoonJung Park
Jung-Hyun Byun
Tack-Don Han
Event Type
Poster
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
In this paper, we propose three display methods for projection-based augmented reality. In spatial augmented reality (SAR), determining where information, objects, or contents are to be displayed is a difficult and important issue. We use deep learning models to estimate user pose and suggest ways to solve the issue based on this data. Finally, each method can be appropriately applied according to various applications and scenarios.
In this paper, we propose three display methods for projection-based augmented reality. In spatial augmented reality (SAR), determining where information, objects, or contents are to be displayed is a difficult and important issue. We use deep learning models to estimate user pose and suggest ways to solve the issue based on this data. Finally, each method can be appropriately applied according to various applications and scenarios.
Contributors
Hyocheol Ro
Yonsei University
Media System Lab
YoonJung Park
Yonsei University
Media System Lab
Jung-Hyun Byun
Yonsei University
Media System Lab
Tack-Don Han
Yonsei University
Media System Lab
56. Fluid-Measurement Technology Using Flow Birefringence of Nanocellulose
SessionHardware Interfaces
Contributors
Shogo Yamashita
Takaaki Kasuga
Shunichi Suwa
Takashi Miyaki
Masaya Nogi
Jun Rekimoto
Event Type
Poster
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We propose a potential fluid measurement technology aimed at supporting biomechanics research on water sports using fluid simulation and motion analysis. We use an optical property of nanocellulose, called flow birefringence, which makes water flows brighter than their surroundings when placed between right and left circularly-polarized plates.
We propose a potential fluid measurement technology aimed at supporting biomechanics research on water sports using fluid simulation and motion analysis. We use an optical property of nanocellulose, called flow birefringence, which makes water flows brighter than their surroundings when placed between right and left circularly-polarized plates.
Contributors
Shogo Yamashita
The University of Tokyo
Takaaki Kasuga
Osaka University
Shunichi Suwa
The University of Tokyo
Sony Computer Science Laboratories, Inc.
Takashi Miyaki
The University of Tokyo
Masaya Nogi
Osaka University
Jun Rekimoto
The University of Tokyo
Sony Computer Science Laboratories, Inc.
57. Immersive Game for Dental Anesthesia Training With Haptic Feedback
SessionHardware Interfaces
Contributors
Allan Tori
Romero Tori
Matheus Ribeiro
Fátima Nunes
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
An immersive and gamified environment that offers a playful way of practicing dental anesthesia technique with or without aids (tactile or visual).
An immersive and gamified environment that offers a playful way of practicing dental anesthesia technique with or without aids (tactile or visual).
Contributors
Allan Tori
Universidade de São Paulo
Escola Politécnica
Romero Tori
Universidade de São Paulo
Escola Politécnica
Matheus Ribeiro
Universidade de São Paulo
EACH
Fátima Nunes
Universidade de São Paulo
EACH
58. MagicPAPER: Tabletop Interactive Projection Device Based on Tangible Interaction
SessionHardware Interfaces
Contributors
Qin Wu
Jiayuan Wang
Sirui Wang
Tong Su
Chenmei Yu
Event Type
Poster
P/V Yes
Research & Education
Adaptive Technology
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
This study proposes a tabletop projection device that can be implemented by combining physical objects with interactive projections. Users can interact on kraft papers using daily tools, such as marker pens, toothbrushes, colored blocks, and square wooden blocks. The input of the proposed device is a multifunction sensor, and the output is a tabletop projector. Using MagicPAPER, four types of interactions are implemented, namely drawing, gesture recognition, brushing, and building blocks. The abstract and poster discuss the design motivations and system descriptions of MagicPAPER.
This study proposes a tabletop projection device that can be implemented by combining physical objects with interactive projections. Users can interact on kraft papers using daily tools, such as marker pens, toothbrushes, colored blocks, and square wooden blocks. The input of the proposed device is a multifunction sensor, and the output is a tabletop projector. Using MagicPAPER, four types of interactions are implemented, namely drawing, gesture recognition, brushing, and building blocks. The abstract and poster discuss the design motivations and system descriptions of MagicPAPER.
Contributors
Qin Wu
Chengdu University of Information Technology
State Key Laboratory of Software Development Environment
Jiayuan Wang
Chengdu University of Information Technology
Sirui Wang
Chengdu University of Information Technology
Tong Su
Chengdu University of Information Technology
Chenmei Yu
State Key Laboratory of Software Development Environment
59. Multi-View Facial Capture Using Binary Spherical Gradient Illumination
SessionHardware Interfaces
Contributors
Alexander Lattas
Mingqian Wang
Stefanos Zafeiriou
Abhijeet Ghosh
Event Type
Poster
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
In this work, we adapt our recently proposed diffuse-specular separation technique using binary spherical gradient illumination for multi-view face capture. We demonstrate that high-resolution facial normal maps acquired using binary gradients exhibit sharper skin mesostructure details compared to polarized spherical gradients while achieving high-quality reflectance separation for realistic rendering of skin appearance.
In this work, we adapt our recently proposed diffuse-specular separation technique using binary spherical gradient illumination for multi-view face capture. We demonstrate that high-resolution facial normal maps acquired using binary gradients exhibit sharper skin mesostructure details compared to polarized spherical gradients while achieving high-quality reflectance separation for realistic rendering of skin appearance.
Contributors
Alexander Lattas
Imperial College London
Mingqian Wang
Imperial College London
Stefanos Zafeiriou
Imperial College London
Abhijeet Ghosh
Imperial College London
Imperial College London
60. Neck Strap Haptics: An Algorithm for Non-Visible VR Information Using Haptic Perception on the Neck
SessionHardware Interfaces
Contributors
Yusuke Yamazaki
Shoichi Hasegawa
Hironori Mitake
Akihiko Shirai
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We propose a new haptic-rendering algorithm that dynamically modulates wave parameters to convey distance, direction, and object type by utilizing neck perception and the Hapbeat-Duo, a haptic device composed of two actuators linked by a neck strap. In our experiment, we presented haptic feedback of sine waves which were dynamically modulated according to direction and distance between a player and a target. Players could reach invisible targets and immediately know they reached them. This method is useful for various VR-use cases because it provides feedback without disturbing users' movement.
We propose a new haptic-rendering algorithm that dynamically modulates wave parameters to convey distance, direction, and object type by utilizing neck perception and the Hapbeat-Duo, a haptic device composed of two actuators linked by a neck strap. In our experiment, we presented haptic feedback of sine waves which were dynamically modulated according to direction and distance between a player and a target. Players could reach invisible targets and immediately know they reached them. This method is useful for various VR-use cases because it provides feedback without disturbing users' movement.
Contributors
Yusuke Yamazaki
GREE, Inc.
Tokyo Institute of Technology
Shoichi Hasegawa
Tokyo Institute of Technology
Hironori Mitake
Tokyo Institute of Technology
Tokyo Institute of Technology
Akihiko Shirai
GREE, Inc.
61. Reconsideration of Ouija Board Motion in Terms of Haptic Illusions (IV): Effect of Haptic Cue and Another Player
SessionHardware Interfaces
Contributors
Hiroyuki Kajimoto
Takahiro Shitara
Vibol Yem
Event Type
Poster
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
The Ouija board game is associated with a type of involuntary motion known as an ideomotor action. We sought to clarify the conditions under which this motion occurs by evaluating the effect that visual and haptic movement cues have on its occurrence. Using our lateral skin deformation device, we found that the simultaneous presentation of visual and tactile illusory motion and force produced larger ideomotor actions than when either modality presented alone, an effect that was further potentiated by the presence of another player (an avatar).
The Ouija board game is associated with a type of involuntary motion known as an ideomotor action. We sought to clarify the conditions under which this motion occurs by evaluating the effect that visual and haptic movement cues have on its occurrence. Using our lateral skin deformation device, we found that the simultaneous presentation of visual and tactile illusory motion and force produced larger ideomotor actions than when either modality presented alone, an effect that was further potentiated by the presence of another player (an avatar).
Contributors
Hiroyuki Kajimoto
The University of Electro-Communications
Takahiro Shitara
Reconsideration of Ouija Board Motion in Terms of Haptic Illusions (IV): Effect of Haptic Cue and Another Player
Vibol Yem
Tokyo Metropolitan University
62. Remote Control Experiment With DisplayBowl and 360-Degree Video
SessionHardware Interfaces
Contributors
Shio Miyafuji
Soichiro Toyohara
Toshiki Sato
Hideki Koike
Event Type
Poster
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
DisplayBowl is a bowl-shaped hemispherical display for showing omnidirectional images with direction data. It provides users with a novel way of observing 360-degree video streams, which improves the awareness of the surroundings when operating a remote-controlled vehicle compared to conventional flat displays and HMDs. In this paper, we present a user study, in which we asked participants to control a remote drone using an omnidirectional video streaming to compare the uniqueness and advantages of three displays: a flat panel display, a head-mounted display, and DisplayBowl.
DisplayBowl is a bowl-shaped hemispherical display for showing omnidirectional images with direction data. It provides users with a novel way of observing 360-degree video streams, which improves the awareness of the surroundings when operating a remote-controlled vehicle compared to conventional flat displays and HMDs. In this paper, we present a user study, in which we asked participants to control a remote drone using an omnidirectional video streaming to compare the uniqueness and advantages of three displays: a flat panel display, a head-mounted display, and DisplayBowl.
Contributors
Shio Miyafuji
Tokyo Institute of Technology
Soichiro Toyohara
Tokyo Institute of Technology
Toshiki Sato
Tokyo Institute of Technology
Hideki Koike
Tokyo Institute of Technology
63. ShareHaptics: A Modular Haptic Feedback System Using ShapeMemory Alloy for Mixed Reality Shared Space Applications
SessionHardware Interfaces
Contributors
Takuro Nakao
Stevanus Kevin
Megumi Isogai
Shinya Shimizu
Hideaki Kimata
Kai Kunze
Yun Suen Pai
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We present ShareHaptics, a novel modular system to provide tactile and pressure feedback in mixed reality applications using a novel actuator: shape memory alloy (SMA). We apply it to fingers, wrist, foot, and ankle. Although it can be used for haptic feedback in a diverse set of use cases, we specifically focus on collaborative applications: ShareHaptics allows to haptically jack in to a remote environment via custom glove and ankle braces. We demonstrate a wide range of applications: watching sports, gaming, collaborative discussions, and skill transfer.
We present ShareHaptics, a novel modular system to provide tactile and pressure feedback in mixed reality applications using a novel actuator: shape memory alloy (SMA). We apply it to fingers, wrist, foot, and ankle. Although it can be used for haptic feedback in a diverse set of use cases, we specifically focus on collaborative applications: ShareHaptics allows to haptically jack in to a remote environment via custom glove and ankle braces. We demonstrate a wide range of applications: watching sports, gaming, collaborative discussions, and skill transfer.
Contributors
Takuro Nakao
Keio University
Stevanus Kevin
Keio University
Megumi Isogai
NTT Media Intelligence Lab
Shinya Shimizu
NTT Media Intelligence Lab
Hideaki Kimata
NTT Media Intelligence Lab
Kai Kunze
Keio University
Yun Suen Pai
Keio University
64. Visualizing Expert Motion for Guidance in a VR Ski Simulator
SessionHardware Interfaces
Contributors
Takayuki Nozawa
Erwin Wu
Florian Perteneder
Hideki Koike
Event Type
Poster
P/V Yes
Gaming & Interactive
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We propose a VR ski training system, which enables users to practice alpine skiing by copying the motions of prerecorded expert skiers. Using an indoor ski simulator, users improve their skills by following a virtual avatar replayed in front of them. We investigate different visualizations to support the learning process.
We propose a VR ski training system, which enables users to practice alpine skiing by copying the motions of prerecorded expert skiers. Using an indoor ski simulator, users improve their skills by following a virtual avatar replayed in front of them. We investigate different visualizations to support the learning process.
Contributors
Takayuki Nozawa
Tokyo Institute of Technology
Erwin Wu
Tokyo Institute of Technology
Florian Perteneder
Tokyo Institute of Technology
Hideki Koike
Tokyo Institute of Technology
65. Wearable Soft Pneumatic Ring With Multi-Mode Controlling for Rich Haptic Effects
SessionHardware Interfaces
Contributors
Aishwari Talhan
Hwangil Kim
Seokhee Jeon
Event Type
Poster
P/V Yes
New Technologies
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We are presenting a pneumatic-actuated, light-weight, multi-mode, and wearable haptic interface of the soft bladder that could generate rich haptic feedback such as force, static pressure, and vibrotactile feedback for VR/AR applications.
We are presenting a pneumatic-actuated, light-weight, multi-mode, and wearable haptic interface of the soft bladder that could generate rich haptic feedback such as force, static pressure, and vibrotactile feedback for VR/AR applications.
Contributors
Aishwari Talhan
Kyung Hee University, Yongin-si
Hwangil Kim
Kyung Hee University, Yongin-si
Seokhee Jeon
Kyung Hee University, Yongin-si
Production
Event TypePoster
P/V Maybe
Production & Animation
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
66. A Procedural Approach to Creating American Second Empire Houses
SessionProduction
Contributors
Madison Kramer
Ergun Akleman
Event Type
Poster
P/V Maybe
P/V Yes
Production & Animation
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We present a procedural approach to design American Second Empire houses. Our procedural approach captures the style differences of Second Empire houses with relatively few parameters. A method to break up these virtual models into slices in order to efficiently and economically 3D print them was also developed. Using this approach, we created miniatures of two landmark buildings: the Hamilton-Turner Inn in Savannah, Georgia, and the Enoch Pratt House in Baltimore.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
We present a procedural approach to design American Second Empire houses. Our procedural approach captures the style differences of Second Empire houses with relatively few parameters. A method to break up these virtual models into slices in order to efficiently and economically 3D print them was also developed. Using this approach, we created miniatures of two landmark buildings: the Hamilton-Turner Inn in Savannah, Georgia, and the Enoch Pratt House in Baltimore.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Contributors
Madison Kramer
Texas A&M University
Ergun Akleman
Texas A&M University
67. Compositing Light Field Video Using Multiplane Images
SessionProduction
Contributors
Matthew DuVall
John Flynn
Michael Broxton
Paul Debevec
Event Type
Poster
P/V Maybe
P/V Yes
Production & Animation
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We present advanced techniques for the manipulation of light field photography and video in the format of multiplane images, using common post-production tools and workflows.
We present advanced techniques for the manipulation of light field photography and video in the format of multiplane images, using common post-production tools and workflows.
Contributors
Matthew DuVall
Google
John Flynn
Google, Inc.
Michael Broxton
Google, Inc.
Paul Debevec
Google, Inc.
68. Efficient Mask Expansion for Green-Screen Keying Using Color Distributions
SessionProduction
Contributors
Alexandre Derouet-Jourdan
Marc Salvati
Xiaoxiong Xing
Takuro Nishikawa
Event Type
Poster
P/V No
P/V Maybe
Production & Animation
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
Masks are heavily used in image and video processing, particularly in the context of green screen keying. Designing good masks is a difficult task that involves painting over small details of images. Usually, only a rough mask is created. We propose an algorithm to expand such a mask using color similarity. Our approach is fast, even on 4K images, and compares favorably with standard tools used in keying.
Masks are heavily used in image and video processing, particularly in the context of green screen keying. Designing good masks is a difficult task that involves painting over small details of images. Usually, only a rough mask is created. We propose an algorithm to expand such a mask using color similarity. Our approach is fast, even on 4K images, and compares favorably with standard tools used in keying.
Contributors
Alexandre Derouet-Jourdan
OLM Digital Inc.
Marc Salvati
OLM Digital Inc.
Xiaoxiong Xing
OLM Digital Inc.
Takuro Nishikawa
OLM Digital Inc.
69. Interactive Cinematic Scientific Visualization in Unity
SessionProduction
Contributors
Jasmine Y. Shih
Kalina Borkiewicz
Andrew Christensen
Donna Cox
Event Type
Poster
P/V Maybe
Production & Animation
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We found that there is value in using a game engine to develop interactive cinematic scientific visualizations for educational purposes through experimenting with Unity's particle system, developing an interactive cinematic visualization of the moon formation, and studying the effects of our interactive visualization on young viewers.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
We found that there is value in using a game engine to develop interactive cinematic scientific visualizations for educational purposes through experimenting with Unity's particle system, developing an interactive cinematic visualization of the moon formation, and studying the effects of our interactive visualization on young viewers.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Contributors
Jasmine Y. Shih
NCSA Advanced Visualization Lab, University of Illinois at Urbana-Champaign
Kalina Borkiewicz
Visualization Programmer
NCSA Advanced Visualization Lab, University of Illinois at Urbana-Champaign
Andrew Christensen
Visualization Programmer
NCSA Advanced Visualization Lab, University of Illinois at Urbana-Champaign
Donna Cox
Director
NCSA Advanced Visualization Lab, University of Illinois at Urbana-Champaign
70. Skinning Vector Graphics With GANs
SessionProduction
Contributors
Ankit Phogat
Vineet Batra
Matthew Fisher
Daniel M. Kaufman
Event Type
Poster
P/V No
P/V Maybe
Production & Animation
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We propose a novel and intuitive method for editing vector graphics, which uses a generative adversarial network to predict salient points, which are used to handle locations for linear blend skinning transformations. Our method decouples the complexity of input geometry from mesh topology and formulates a linear optimization problem for curve fitting, ensuring robust, real-time feedback.
We propose a novel and intuitive method for editing vector graphics, which uses a generative adversarial network to predict salient points, which are used to handle locations for linear blend skinning transformations. Our method decouples the complexity of input geometry from mesh topology and formulates a linear optimization problem for curve fitting, ensuring robust, real-time feedback.
Contributors
Ankit Phogat
Adobe
Vineet Batra
Adobe
Matthew Fisher
Adobe
Daniel M. Kaufman
Adobe
71. Visual Simulation of Ice and Frost With Sketch Input
SessionProduction
Contributors
Mikiko Amano
Takayuki Itoh
Event Type
Poster
P/V Maybe
P/V Yes
Production & Animation
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
In this poster, we propose a tool for 3DCG in which users can intuitively reproduce the phenomena, including crystals of ice and frost sticking to and spreading on object surfaces by applying a simple sketch interface and a physically-based simulation.
In this poster, we propose a tool for 3DCG in which users can intuitively reproduce the phenomena, including crystals of ice and frost sticking to and spreading on object surfaces by applying a simple sketch interface and a physically-based simulation.
Contributors
Mikiko Amano
Ochanomizu University
Takayuki Itoh
Ochanomizu University
72. Voxel Printing Using Procedural Art-Directable Technologies
SessionProduction
Contributors
Tor Robinson
William Furneaux
Event Type
Poster
P/V Maybe
P/V Yes
Production & Animation
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
A procedural art-directable workflow is developed for voxel 3D printing using existing digital effects technologies. Customized for the Stratasys J750's unique materials, the system produces large-scale prosthetic eyes as a case study for film and display work.
A procedural art-directable workflow is developed for voxel 3D printing using existing digital effects technologies. Customized for the Stratasys J750's unique materials, the system produces large-scale prosthetic eyes as a case study for film and display work.
Contributors
Tor Robinson
Weta Workshop
William Furneaux
Weta Workshop
Research
Event TypePoster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
73. A Dataset for Benchmarking Time-Resolved Non-Line-of-Sight Imaging
SessionResearch
Contributors
Miguel Galindo
Julio Marco
Matthew O'Toole
Gordon Wetzstein
Diego Gutierrez
Adrian Jarabo
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
Time-resolved imaging has made it possible to look around corners by exploiting information from diffuse light bounces, but so far, it has only been proven to work in very simple scenarios. We present a public dataset of complex synthetic time-resolved non-line-of-sight scenes aimed at benchmarking reconstructions in real-world scenarios.
Time-resolved imaging has made it possible to look around corners by exploiting information from diffuse light bounces, but so far, it has only been proven to work in very simple scenarios. We present a public dataset of complex synthetic time-resolved non-line-of-sight scenes aimed at benchmarking reconstructions in real-world scenarios.
Contributors
Miguel Galindo
Universidad de Zaragoza, I3A
Julio Marco
Universidad de Zaragoza, I3A
Matthew O'Toole
Carnegie Mellon University
Gordon Wetzstein
Stanford University
Diego Gutierrez
Universidad de Zaragoza, I3A
Adrian Jarabo
Universidad de Zaragoza, I3A
74. A Similarity Measure for Material Appearance
SessionResearch
Contributors
Manuel Lagunas
Sandra Malpica
Ana Serrano
Elena Garces
Diego Gutierrez
Belen Masia
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We present a deep learning-based model to measure the similarity in appearance between different materials, which correlates with human similarity judgments. Our evaluation shows that our model outperforms existing metrics. Last, we demonstrate several applications enabled by our metric, including appearance-based search for material suggestions, database visualization, clustering and summarization, and gamut mapping.
We present a deep learning-based model to measure the similarity in appearance between different materials, which correlates with human similarity judgments. Our evaluation shows that our model outperforms existing metrics. Last, we demonstrate several applications enabled by our metric, including appearance-based search for material suggestions, database visualization, clustering and summarization, and gamut mapping.
Contributors
Manuel Lagunas
Universidad de Zaragoza
Sandra Malpica
Universidad de Zaragoza
Ana Serrano
Universidad de Zaragoza
Elena Garces
Universidad de Zaragoza
Diego Gutierrez
Universidad de Zaragoza
Belen Masia
Universidad de Zaragoza
75. Affine Interpolation in a Lie Group Framework
SessionResearch
Contributors
Sumukh Bansal
Aditya Tatu
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
An interpolation framework based on a Lie group representation of the affine transformation is proposed, which, while preserving several interpolation properties, also ensures an interpolation in all of the cases.
An interpolation framework based on a Lie group representation of the affine transformation is proposed, which, while preserving several interpolation properties, also ensures an interpolation in all of the cases.
Contributors
Sumukh Bansal
Dhirubhai Ambani Institute of Information and Communication Technology Gandhinagar
Aditya Tatu
Dhirubhai Ambani Institute of Information and Communication Technology Gandhinagar
76. An Adaptive Variational Finite Difference Framework for Efficient Symmetric Octree Viscosity
SessionResearch
Contributors
Ryan Goldade
Yipeng Wang
Mridul Aanjaneya
Christopher Batty
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We present a convergent variational discretization strategy for fluid viscosity on octree grids that ensures symmetric, positive, definite linear systems and offers close to an order of magnitude performance improvement.
We present a convergent variational discretization strategy for fluid viscosity on octree grids that ensures symmetric, positive, definite linear systems and offers close to an order of magnitude performance improvement.
Contributors
Ryan Goldade
University of Waterloo
Yipeng Wang
University of Waterloo
Mridul Aanjaneya
Rutgers University
Christopher Batty
University of Waterloo
77. Coding Scheme Optimization for Fast Fluorescence Lifetime Imaging
SessionResearch
Contributor
Jongho Lee
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We design novel and high-performance coding schemes for fast fluorescence lifetime imaging that achieve up to an order of magnitude shorter acquisition time as compared to existing approaches.
We design novel and high-performance coding schemes for fast fluorescence lifetime imaging that achieve up to an order of magnitude shorter acquisition time as compared to existing approaches.
Contributor
Jongho Lee
University of Wisconsin-Madison
78. Computational Design of Fabric Formwork
SessionResearch
Contributors
Xiaoting Zhang
Guoxin Fang
Melina Skouras
Gwenda Gieseler
Charlie Wang
Emily Whiting
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We present an inverse design tool for fabric formwork – a process where flat panels are sewn together to form a fabric container for casting a plaster sculpture. Our computational framework generates optimized flat panels and fabrication orientation with reference to a target shape, and determines effective locations for external supports. We demonstrate the function of this design tool on a variety of models with different shapes and topology. Physical fabrication is also demonstrated to validate our approach.
We present an inverse design tool for fabric formwork – a process where flat panels are sewn together to form a fabric container for casting a plaster sculpture. Our computational framework generates optimized flat panels and fabrication orientation with reference to a target shape, and determines effective locations for external supports. We demonstrate the function of this design tool on a variety of models with different shapes and topology. Physical fabrication is also demonstrated to validate our approach.
Contributors
Xiaoting Zhang
Boston University
Guoxin Fang
Delft University of Technology
Melina Skouras
INRIA
Gwenda Gieseler
Delft University of Technology
Charlie Wang
The Chinese University of Hong Kong
Emily Whiting
Boston University
79. Content-Aware Generative Modeling of Graphic Design Layouts
SessionResearch
Contributors
Xinru Zheng
Xiaotian Qiao
Ying Cao
Rynson Lau
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We present a content-aware deep generative model of graphic design layouts, which is able to synthesize high-quality, professional layouts based on the contents of input images and text.
We present a content-aware deep generative model of graphic design layouts, which is able to synthesize high-quality, professional layouts based on the contents of input images and text.
Contributors
Xinru Zheng
City University of Hong Kong
Xiaotian Qiao
City University of Hong Kong
Ying Cao
City University of Hong Kong
Rynson Lau
City University of Hong Kong
80. Convergent Turbulence Refinement Toward Irrotational Vortex
SessionResearch
Contributors
Xiaokun Wang
Sinuo Liu
Xiaojuan Ban
Yanrui Xu
Jing Zhou
Cong Wang
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We proposed a detail refinement method to enhance the visual effect of turbulence in irrotational vortex. We restore the missing angular velocity from the particles and convert them into linear velocity to recover turbulent detail due to numerical disspation. Vorticity field is employed to approximate angular velocity which is fed back to the velocity field using the irrotational vortex model.
We proposed a detail refinement method to enhance the visual effect of turbulence in irrotational vortex. We restore the missing angular velocity from the particles and convert them into linear velocity to recover turbulent detail due to numerical disspation. Vorticity field is employed to approximate angular velocity which is fed back to the velocity field using the irrotational vortex model.
Contributors
Xiaokun Wang
University of Science and Technology Beijing
Beijing Advanced Innovation Center for Materials Genome Engineering
Sinuo Liu
University of Science and Technology Beijing
Beijing Advanced Innovation Center for Materials Genome Engineering
Xiaojuan Ban
University of Science and Technology Beijing
Beijing Advanced Innovation Center for Materials Genome Engineering
Yanrui Xu
University of Science and Technology Beijing
Beijing Advanced Innovation Center for Materials Genome Engineering
Jing Zhou
University of Science and Technology Beijing
Beijing Advanced Innovation Center for Materials Genome Engineering
Cong Wang
University of Science and Technology Beijing
Beijing Advanced Innovation Center for Materials Genome Engineering
81. Delaunay Lofts: A New Class of Space-Filling Shapes
SessionResearch
Contributors
Sai Ganesh Subramanian
Matthew R. Eng
Vinayak Krishnamurthy
ERGUN Akleman
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
This is an approach to construct and design a new class of space-filling shapes. The approach is based on interpolation of a stack of planar tiles whose dual tilings are Delaunay diagrams. Control curves that interpolate Delaunay vertices are constructed. Voronoi decomposition of the volume using these control curves as Voronoi sites gives us lofted interpolation of original polygons in planar tiles. This, combined with the use of wallpaper symmetries, allows for the design of space-filling shapes in three-space.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
This is an approach to construct and design a new class of space-filling shapes. The approach is based on interpolation of a stack of planar tiles whose dual tilings are Delaunay diagrams. Control curves that interpolate Delaunay vertices are constructed. Voronoi decomposition of the volume using these control curves as Voronoi sites gives us lofted interpolation of original polygons in planar tiles. This, combined with the use of wallpaper symmetries, allows for the design of space-filling shapes in three-space.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Contributors
Sai Ganesh Subramanian
Texas A&M University
Matthew R. Eng
Texas A&M University
Vinayak Krishnamurthy
Texas A&M University
ERGUN Akleman
Texas A&M University
Texas A&M University
82. Effectiveness of Facial Animated Avatar and Transformed Voice in eLearning Programming Course
SessionResearch
Contributors
Rex Hsieh
Akihiko Shirai
Hisashi Sato
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
This article reports the effectiveness of facial animated avatar and transformed voice in eLearning programming courses. It tests three (real male professor, male avatar, female avatar) visuals with voice (original male voice, transformed) by a VT-4 vocoder. It tested in 15 groups by 186 students. Female-type avatar was the most visually appealing avatar; its combination with voice transformation severely hinders its overall score. This research can be extended to real-time live with preferences of students and draw more connections between student perception of avatars and actual lecturers.
This article reports the effectiveness of facial animated avatar and transformed voice in eLearning programming courses. It tests three (real male professor, male avatar, female avatar) visuals with voice (original male voice, transformed) by a VT-4 vocoder. It tested in 15 groups by 186 students. Female-type avatar was the most visually appealing avatar; its combination with voice transformation severely hinders its overall score. This research can be extended to real-time live with preferences of students and draw more connections between student perception of avatars and actual lecturers.
Contributors
Rex Hsieh
Kanagawa Institute of Technology
Akihiko Shirai
GREE, Inc.
GREE VR Studio Lab
Hisashi Sato
Kanagawa Institute of Technology
83. Enhancement of CT Images for Visualization
SessionResearch
Contributors
Anam Mehmood
Ishtiaq Rasool Khan
Hassan Dawood
Hussain Dawood
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
Modern medical science depends on imaging technologies for an accurate diagnosis. Medical images require post-processing – like edge and contrast enhancement and noise removal – for visualization. We proposed a divisive clustering-based contrast enhancement technique for computed tomography (CT) images. Our algorithm efficiently enhances both low- and high-intensity regions and preserves the edges very well.
Modern medical science depends on imaging technologies for an accurate diagnosis. Medical images require post-processing – like edge and contrast enhancement and noise removal – for visualization. We proposed a divisive clustering-based contrast enhancement technique for computed tomography (CT) images. Our algorithm efficiently enhances both low- and high-intensity regions and preserves the edges very well.
Contributors
Anam Mehmood
University of Eng. & Technology Taxila
Ishtiaq Rasool Khan
University of Jeddah
Hassan Dawood
University of Eng. & Technology Taxila
Hussain Dawood
University of Jeddah
84. KleinPAT: Optimal Mode Conflation for Time-Domain Precomputation of Acoustic Transfer
SessionResearch
Contributors
Jui-Hsien Wang
Doug L. James
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We propose KleinPAT - a blazingly fast acoustic transfer solver that generates high-quality, rigid-body sound models in a matter of minutes rather than days (>2,000x speedup achieved) using a novel "conflate-simulate-deconflate" algorithm and an optimized GPU implementation.
We propose KleinPAT - a blazingly fast acoustic transfer solver that generates high-quality, rigid-body sound models in a matter of minutes rather than days (>2,000x speedup achieved) using a novel "conflate-simulate-deconflate" algorithm and an optimized GPU implementation.
Contributors
Jui-Hsien Wang
Stanford University
Doug L. James
Stanford University
85. Luminance-Contrast-Aware Foveated Rendering
SessionResearch
Contributors
Okan Tarhan Tursun
Elena Arabadzhiyska-Koleva
Marek Wernikowski
Radosław Mantiuk
Hans-Peter Seidel
Karol Myszkowski
Piotr Didyk
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We present a new foveated-rendering technique that improves the perceived quality and rendering cost by adjusting the amount of quality degradation according to the underlying content.
We present a new foveated-rendering technique that improves the perceived quality and rendering cost by adjusting the amount of quality degradation according to the underlying content.
Contributors
Okan Tarhan Tursun
Max Planck Institute for Informatics
Elena Arabadzhiyska-Koleva
Saarland University, MMCI
Max Planck Institute for Informatics
Marek Wernikowski
West Pomeranian University of Technology
Radosław Mantiuk
West Pomeranian University of Technology
Hans-Peter Seidel
Max Planck Institute for Informatics
Karol Myszkowski
Max Planck Institute for Informatics
Piotr Didyk
Università della Svizzera italiana
86. Mixing Sauces: A Viscosity Blending Model for Shear Thinning Fluids
SessionResearch
Contributors
Kentaro Nagasawa
Takayuki Suzuki
Ryohei Seto
Masato Okada
Yonghao Yue
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We propose a nonlinear blending model for describing the measured flowing properties of mixtures of shear thinning fluids, whose behaviors can be different from their constituents alone.
We propose a nonlinear blending model for describing the measured flowing properties of mixtures of shear thinning fluids, whose behaviors can be different from their constituents alone.
Contributors
Kentaro Nagasawa
The University of Tokyo
Takayuki Suzuki
The University of Tokyo
Ryohei Seto
Kyoto University
Masato Okada
The University of Tokyo
Yonghao Yue
The University of Tokyo
Aoyama Gakuin University
87. Multi-Resolution Approach to Computing Locally Injective Maps on Meshes
SessionResearch
Contributors
Alexander Naitsat
Yehoshua Y. Zeevi
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
In this work, we propose a multi-resolution approach to the construction of injective maps with low distortions on meshes. We initialize the induced optimization problem with the solution of the same problem in a lower resolution. Our main focus is the multi-resolution surface parametrization. We overcome the non-injective initialization obstacle, often occurring during transitions between multiple resolutions, by simultaneously repairing inverted elements, minimizing geometric distortions, and employing the proposed embedding optimization techniques.
In this work, we propose a multi-resolution approach to the construction of injective maps with low distortions on meshes. We initialize the induced optimization problem with the solution of the same problem in a lower resolution. Our main focus is the multi-resolution surface parametrization. We overcome the non-injective initialization obstacle, often occurring during transitions between multiple resolutions, by simultaneously repairing inverted elements, minimizing geometric distortions, and employing the proposed embedding optimization techniques.
Contributors
Alexander Naitsat
Technion
Yehoshua Y. Zeevi
Technion
88. Noise Reduction With Image Inpainting: An Application in Clinical Data Diagnosis
SessionResearch
Contributors
Jing Ke
Junwei Deng
Yizhou Lu
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We design a novel model to detect and remove the false positives in clinical images to offer better assistance to both computer-aided methods and human experts. The automatic detection of cervical cancer is used as a case study and experimentally shows the effectiveness.
We design a novel model to detect and remove the false positives in clinical images to offer better assistance to both computer-aided methods and human experts. The automatic detection of cervical cancer is used as a case study and experimentally shows the effectiveness.
Contributors
Jing Ke
Shanghai Jiao Tong University
University of New South Wales
Junwei Deng
Shanghai Jiao Tong University
University of Michigan
Yizhou Lu
Shanghai Jiao Tong University
89. OceanGAN: A Deep Learning Alternative to Physics-Based Ocean Rendering
SessionResearch
Contributors
Christopher R. Ratto
Mimi Szeto
David M. Slocum
Kevin A. Del Bene
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
This work proposes using generative adversarial networks (GANs) as an alternative to physics-based raytracing for rendering large ocean scenes with ambient breaking waves. The GAN-generated ocean imagery was generated nearly an order of magnitude faster than raytracing, and the results were successfully validated against raytraced imagery in the spectral domain.
This work proposes using generative adversarial networks (GANs) as an alternative to physics-based raytracing for rendering large ocean scenes with ambient breaking waves. The GAN-generated ocean imagery was generated nearly an order of magnitude faster than raytracing, and the results were successfully validated against raytraced imagery in the spectral domain.
Contributors
Christopher R. Ratto
The Johns Hopkins University Applied Physics Laboratory
Mimi Szeto
The Johns Hopkins University Applied Physics Laboratory
David M. Slocum
The Johns Hopkins University Applied Physics Laboratory
Kevin A. Del Bene
The Johns Hopkins University Applied Physics Laboratory
90. Physically Based Statistical Simulation of Rain Sound
SessionResearch
Contributors
Shiguang Liu
Haonan Cheng
Yiying Tong
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
This paper proposes an efficient scheme for rendering rain sounds in 3D virtual environments with perceptually salient near-field effects using a novel-proposed, physically-based statistical simulation method.
This paper proposes an efficient scheme for rendering rain sounds in 3D virtual environments with perceptually salient near-field effects using a novel-proposed, physically-based statistical simulation method.
Contributors
Shiguang Liu
Tianjin University
Haonan Cheng
Tianjin University
Yiying Tong
Michigan State University
91. Physics-based Full-body Soccer Motion Control for Dribbling and Shooting
SessionResearch
Contributors
Seokpyo Hong
Daseong Han
Kyungmin Cho
Joseph S. Shin
Junyong Noh
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY AND TUESDAY, 30 JULY, 12:15-1:15 PM
We present a novel motion control system that produces physically-correct full-body soccer motions: dribbling forward, dribbling to the side, and shooting. This system performs two tightly-coupled tasks: data-driven motion prediction and physics-based motion synthesis. The former synthesizes a reference motion and further refines the motion to make the character kick the ball at a right time and place. Provided with the reference motion, the latter then adopts a Model Predictive Control (MPC) framework to generate a physically-correct soccer motion, by solving an optimal control problem based on dynamics for a full-body character and the moving ball together with their interactions.
We present a novel motion control system that produces physically-correct full-body soccer motions: dribbling forward, dribbling to the side, and shooting. This system performs two tightly-coupled tasks: data-driven motion prediction and physics-based motion synthesis. The former synthesizes a reference motion and further refines the motion to make the character kick the ball at a right time and place. Provided with the reference motion, the latter then adopts a Model Predictive Control (MPC) framework to generate a physically-correct soccer motion, by solving an optimal control problem based on dynamics for a full-body character and the moving ball together with their interactions.
Contributors
Seokpyo Hong
Korea Advanced Institute of Science and Technology
Daseong Han
Handong Global University
Kyungmin Cho
Korea Advanced Institute of Science and Technology
Joseph S. Shin
Korea Advanced Institute of Science and Technology
Handong Global University
Junyong Noh
Korea Advanced Institute of Science and Technology
92. Real-Time Structure Aware Color Stippling
SessionResearch
Contributors
Lei Ma
Hong Deng
Beibei Wang
Yanyun Chen
Tamy Boubekeur
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We have presented a color-stippling method using a color space thresholding strategy for pregenerated samples, which allow for the stippling editing with arbitrary input color vector.
We have presented a color-stippling method using a color space thresholding strategy for pregenerated samples, which allow for the stippling editing with arbitrary input color vector.
Contributors
Lei Ma
Center on Frontiers of Computing Studies, Peking University
AICFVE, Beijing Film Academy
Hong Deng
Nanjing University of Science and Technology
Beibei Wang
Nanjing University of Science and Technology
Yanyun Chen
State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences
Tamy Boubekeur
LTCI, Telecom ParisTech, Paris-Saclay University
93. RedMax: Efficient & Flexible Approach for Articulated Dynamics
SessionResearch
Contributors
Ying Wang
Nicholas J. Weidner
Margaret Baxter
Yura Hwang
Danny M. Kaufman
Shinjiro Sueda
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We propose an efficient and flexible approach that works in reduced/maximal coordinates with fully implicit two-way coupling of articulated and deformable bodies.
We propose an efficient and flexible approach that works in reduced/maximal coordinates with fully implicit two-way coupling of articulated and deformable bodies.
Contributors
Ying Wang
Texas A&M University
Nicholas J. Weidner
Texas A&M University
Margaret Baxter
Texas A&M University
Yura Hwang
Texas A&M University
Danny M. Kaufman
Adobe Research
Shinjiro Sueda
Texas A&M University
94. Semantic Photo Manipulation With a Generative Image Prior
SessionResearch
Contributors
David Bau
Hendrik Strobelt
William Peebles
Jonas Wulff
Bolei Zhou
Jun-Yan Zhu
Antonio Torralba
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: TUESDAY, 30 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We propose a method to enable semantic photo manipulation by using a generative adversarial network to generate semantic features like trees, windows, chairs, etc. Our method can accurately reconstruct a user-given input image and synthesize new content, consistent with the appearance of the input image.
We propose a method to enable semantic photo manipulation by using a generative adversarial network to generate semantic features like trees, windows, chairs, etc. Our method can accurately reconstruct a user-given input image and synthesize new content, consistent with the appearance of the input image.
Contributors
David Bau
MIT CSAIL
MIT-IBM Watson AI Lab
Hendrik Strobelt
IBM Research
MIT-IBM Watson AI Lab
William Peebles
MIT CSAIL
Jonas Wulff
MIT CSAIL
Bolei Zhou
Chinese University of Hong Kong
Jun-Yan Zhu
MIT CSAIL
Antonio Torralba
MIT CSAIL
MIT-IBM Watson AI Lab
95. TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures
SessionResearch
Contributors
Anna Frühstück
Ibraheem Alhashim
Peter Wonka
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
We tackle the problem of texture synthesis in the setting where many input images are given and a large-scale output is required. Building on recent generative adversarial networks, we propose: an algorithm to combine outputs of GANs trained on a smaller resolution to produce a large-scale plausible texture map with virtually no boundary artifacts; and a user interface to enable artistic control. Our quantitative and qualitative results showcase the generation of synthesized high-resolution maps consisting of up to hundreds of megapixels as a case in point.
We tackle the problem of texture synthesis in the setting where many input images are given and a large-scale output is required. Building on recent generative adversarial networks, we propose: an algorithm to combine outputs of GANs trained on a smaller resolution to produce a large-scale plausible texture map with virtually no boundary artifacts; and a user interface to enable artistic control. Our quantitative and qualitative results showcase the generation of synthesized high-resolution maps consisting of up to hundreds of megapixels as a case in point.
Contributors
Anna Frühstück
KAUST
Ibraheem Alhashim
KAUST
Peter Wonka
KAUST
96. Unsupervised Incremental Learning for Hand Shape and Pose Estimation
SessionResearch
Contributors
Pratik Kalshetti
Parag Chaudhuri
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
The first unsupervised incremental learning method for refining hand shape and pose estimation obtained from a state-of-the-art hand tracking system by using a model-fitting strategy in a neural network framework is presented.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
The first unsupervised incremental learning method for refining hand shape and pose estimation obtained from a state-of-the-art hand tracking system by using a model-fitting strategy in a neural network framework is presented.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Contributors
Pratik Kalshetti
Indian Institute of Technology Bombay
Parag Chaudhuri
Indian Institute of Technology Bombay
97. VFX Fractal Toolkit: Integrating Fractals Into VFX Pipeline
SessionResearch
Contributor
Juraj Tomori
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and WEDNESDAY, 31 JULY, 12:15-1:15 PM
This work proposes an innovative industry practice regarding fractal geometry-generating and rendering processes. VFX Fractal Toolkit (VFT) aims to provide powerful, yet artist-friendly workflows for exploration and generation of vast amounts of fractals. VFT allows for node-based descriptions of fractals and is built specifically for visual effects pipelines.
This work proposes an innovative industry practice regarding fractal geometry-generating and rendering processes. VFX Fractal Toolkit (VFT) aims to provide powerful, yet artist-friendly workflows for exploration and generation of vast amounts of fractals. VFT allows for node-based descriptions of fractals and is built specifically for visual effects pipelines.
Contributor
Juraj Tomori
Filmakademie Baden-Württemberg GmbH
98. Volume-Aware Design of Composite Molds
SessionResearch
Contributors
Thomas Alderighi
Luigi Malomo
Daniela Giorgi
Bernd Bickel
Paolo Cignoni
Nico Pietroni
Event Type
Poster
P/V Yes
Research & Education
TimeSunday, 28 July 20191:30pm - 5:30pm
LocationSouth Hall J
DescriptionPOSTER SESSIONS: MONDAY, 29 JULY and TUESDAY, 30 JULY, 12:15-1:15 PM
We propose a novel technique for the automatic design of flexible silicone molds. The technique generates composite, two-piece molds. Each mold piece is made up of a hard plastic shell and a flexible silicone part. The algorithm for the automatic generation of the silicone cuts layout is based on a volumetric analysis, geometrically approximating the behavior of the mold volume elements during extraction. The approach is able to robustly handle very complex shapes, improving over the state-of-the-art results.
We propose a novel technique for the automatic design of flexible silicone molds. The technique generates composite, two-piece molds. Each mold piece is made up of a hard plastic shell and a flexible silicone part. The algorithm for the automatic generation of the silicone cuts layout is based on a volumetric analysis, geometrically approximating the behavior of the mold volume elements during extraction. The approach is able to robustly handle very complex shapes, improving over the state-of-the-art results.
Contributors
Thomas Alderighi
Università di Pisa
ISTI-CNR, Pisa
Luigi Malomo
ISTI-CNR
Daniela Giorgi
ISTI-CNR
Bernd Bickel
IST Austria
Paolo Cignoni
ISTI-CNR
Nico Pietroni
UTS Sydney