ACM SIGGRAPH Frontiers Talks

ACM SIGGRAPH Frontiers, Frontiers Talk: Talk: Speculative Futures

Event TypeACM SIGGRAPH Frontiers, Frontiers Talk

Photography and Recording Policies

Interest Areas

Primary Interest Areas

Registration Levels

TimeSunday, 28 July 20198am - 8:45am

LocationTheatre 411

DescriptionWhat is the future we are about to confront, socially, technologically and elsewhere and what opportunities lay ahead as a result? How do we make sense of, and contribute to those opportunities?

ACM SIGGRAPH Frontiers

Frontiers Talk

: Talk: Speculative Futures

Presenter

Joe Tankersley

Event Type

ACM SIGGRAPH Frontiers

Frontiers Talk

Photography and Recording Policies

Interest Areas

Primary Interest Areas

Registration Levels

TimeSunday, 28 July 20198am - 8:45am

LocationTheatre 411

DescriptionWhat is the future we are about to confront, socially, technologically and elsewhere and what opportunities lay ahead as a result? How do we make sense of, and contribute to those opportunities?

Presenter

Joe Tankersley

Unique Visions, Inc.

Joe tankersley is a futurist, author, and former Walt Disney Imagineer. During his twenty-year career at Imagineering he led creative teams on projects at Walt Disney World in Orlando, FL. He also helped to create the first strategic foresight group for WDI and worked with divisions across the Disney company to explore the future of entertainment, business, and creativity. He currently serves as a foresight advisor to multinational corporations, nonprofits, and community groups. He uses his experience as a futurist and storyteller to help his clients create their best tomorrows. Joe has served on the board of directors of the Association of Professional Futurists and the Global Future Forum. He currently serves on the boards of The Blue Ocean Consortium and the Federal Alliance for Safe Homes. He is the author of "Reimagining Our Tomorrows: Making Sure Your Future Doesn’t Suck"

ACM SIGGRAPH Frontiers, Frontiers Talk: Talk: VR Rx: Things you Don’t Know About Patients

Event TypeACM SIGGRAPH Frontiers, Frontiers Talk

Photography and Recording Policies

Interest Areas

Primary Interest Areas

Registration Levels

TimeMonday, 29 July 20198am - 8:45am

LocationTheatre 411

DescriptionThe evolution of VR and emerging technologies from a patients point of view is discussed.

ACM SIGGRAPH Frontiers

Frontiers Talk

: Talk: VR Rx: Things you Don’t Know About Patients

Presenter

Diane Gromala

Event Type

ACM SIGGRAPH Frontiers

Frontiers Talk

Photography and Recording Policies

Interest Areas

Primary Interest Areas

Registration Levels

TimeMonday, 29 July 20198am - 8:45am

LocationTheatre 411

DescriptionThe evolution of VR and emerging technologies from a patients point of view is discussed.

Presenter

Diane Gromala

Simon Frasier University

ACM SIGGRAPH Frontiers, Frontiers Talk: Talk: How Computer Graphics Expertise Will Further the State of the Art in Machine Learning

Event TypeACM SIGGRAPH Frontiers, Frontiers Talk

Photography and Recording Policies

Interest Areas

Primary Interest Areas

Registration Levels

TimeTuesday, 30 July 20198am - 8:45am

LocationTheatre 411

DescriptionWith the success of deep learning for many problems that had long defied solution with classical approaches, machine learning has become an essential tool in many disciplines. The recent increase in papers using this tool at SIGGRAPH is testament to its growing importance in computer graphics.

In this session, I will discuss knowledge transfer in the opposite direction: what insights can experts in computer graphics bring to the field of machine learning? How can knowledge about geometry, rendering, simulation, or perception be used to further the state of the art in machine learning?

ACM SIGGRAPH Frontiers

Frontiers Talk

: Talk: How Computer Graphics Expertise Will Further the State of the Art in Machine Learning

Presenter

Martin Wicke

Event Type

ACM SIGGRAPH Frontiers

Frontiers Talk

Photography and Recording Policies

Interest Areas

Primary Interest Areas

Registration Levels

TimeTuesday, 30 July 20198am - 8:45am

LocationTheatre 411

DescriptionWith the success of deep learning for many problems that had long defied solution with classical approaches, machine learning has become an essential tool in many disciplines. The recent increase in papers using this tool at SIGGRAPH is testament to its growing importance in computer graphics.

In this session, I will discuss knowledge transfer in the opposite direction: what insights can experts in computer graphics bring to the field of machine learning? How can knowledge about geometry, rendering, simulation, or perception be used to further the state of the art in machine learning?

Presenter

Martin Wicke

Google

Martin Wicke is responsible for TensorFlow's APIs and leads its core engineering team. Before joining Google, Martin worked in startups in various areas such as code synthesis, VR, 3D printing, robotics, CAD, and video analysis. He completed his PhD on modeling and animation at ETH Zurich, and afterwards worked on computational geometry and sensor networks at Stanford, and physics simulation at Berkeley.

ACM SIGGRAPH Frontiers, Frontiers Talk: Talk: Visual Strategy

Event TypeACM SIGGRAPH Frontiers, Frontiers Talk

Photography and Recording Policies

Interest Areas

Primary Interest Areas

Registration Levels

TimeTuesday, 30 July 20198am - 8:45am

LocationRoom 153

DescriptionCreative ways of communicating, and working to transform complex concepts into meaningful stories that can be universally understood.

ACM SIGGRAPH Frontiers

Frontiers Talk

: Talk: Visual Strategy

Presenter

Dan Goods

Event Type

ACM SIGGRAPH Frontiers

Frontiers Talk

Photography and Recording Policies

Interest Areas

Primary Interest Areas

Registration Levels

TimeTuesday, 30 July 20198am - 8:45am

LocationRoom 153

DescriptionCreative ways of communicating, and working to transform complex concepts into meaningful stories that can be universally understood.

Presenter

Dan Goods

NASA

DirectedPlay

ACM SIGGRAPH Frontiers, Frontiers Talk: Talk: Imaging a Black Hole with the Event Horizon Telescope

Event TypeACM SIGGRAPH Frontiers, Frontiers Talk

Photography and Recording Policies

Interest Areas

Primary Interest Areas

Registration Levels

TimeWednesday, 31 July 20198am - 8:45am

LocationRoom 408AB

DescriptionThis talk will present the methods and procedures used to produce the first images from the Event Horizon Telescope. It is theorized that a black hole will leave a "shadow" on a background of hot gas. Unfortunately, due to its small size, traditional imaging approaches require an Earth-sized radio telescope. In this talk, I discuss techniques we have developed to photograph a black hole using the Event Horizon Telescope, a network of telescopes scattered across the globe. Imaging a black hole’s structure with this computational telescope requires us to reconstruct images from sparse measurements, heavily corrupted by atmospheric error.

ACM SIGGRAPH Frontiers

Frontiers Talk

: Talk: Imaging a Black Hole with the Event Horizon Telescope

Presenter

Katherine Bouman

Event Type

ACM SIGGRAPH Frontiers

Frontiers Talk

Photography and Recording Policies

Interest Areas

Primary Interest Areas

Registration Levels

TimeWednesday, 31 July 20198am - 8:45am

LocationRoom 408AB

DescriptionThis talk will present the methods and procedures used to produce the first images from the Event Horizon Telescope. It is theorized that a black hole will leave a "shadow" on a background of hot gas. Unfortunately, due to its small size, traditional imaging approaches require an Earth-sized radio telescope. In this talk, I discuss techniques we have developed to photograph a black hole using the Event Horizon Telescope, a network of telescopes scattered across the globe. Imaging a black hole’s structure with this computational telescope requires us to reconstruct images from sparse measurements, heavily corrupted by atmospheric error.

Presenter

Katherine Bouman

California Institute of Technology

Katie Bouman is an assistant professor at Caltech. She was previously a postdoctoral fellow in the Harvard-Smithsonian Center for Astrophysics. She received her Ph.D. in the Computer Science and Artificial Intelligence Laboratory (CSAIL) lab at MIT. The focus of her research is on using emerging computational methods for interdisciplinary imaging.

ACM SIGGRAPH Frontiers, Frontiers Talk: Talk: Metric Telepresence

Event TypeACM SIGGRAPH Frontiers, Frontiers Talk

Photography and Recording Policies

Interest Areas

Primary Interest Areas

Registration Levels

TimeThursday, 1 August 20198am - 8:45am

LocationTheatre 411

DescriptionIn this talk, early steps taken at FRL Pittsburgh in achieving such metric telepresence: realtime social interactions in AR/VR with avatars that look like you, move like you, and sound like you are discussed. Our approach to this problem centers around codec avatars: the use of neural networks to address the computer vision (encoding) and computer graphics (decoding) problems in signal transmission and reception. The creation of codec avatars require capture systems of unprecedented 3D sensing resolution, are also described.

ACM SIGGRAPH Frontiers

Frontiers Talk

: Talk: Metric Telepresence

Presenter

Yaser Sheikh

Event Type

ACM SIGGRAPH Frontiers

Frontiers Talk

Photography and Recording Policies

Interest Areas

Primary Interest Areas

Registration Levels

TimeThursday, 1 August 20198am - 8:45am

LocationTheatre 411

DescriptionTelepresence has the potential to bring billions of people into AR and VR. It is the next step in the evolution from telegraphy to telephony to videoconferencing. Just like telephony and video-conferencing, the key attribute of success will be “authenticity”: users' trust that received signals (e.g., audio for the telephone and video/audio for VC) are truly those transmitted by their friends, colleagues, or family. The challenge arises from this seeming contradiction: how do we enable authentic interactions in artificial environments?

In this talk, early steps taken at FRL Pittsburgh in achieving such metric telepresence: realtime social interactions in AR/VR with avatars that look like you, move like you, and sound like you are discussed. Our approach to this problem centers around codec avatars: the use of neural networks to address the computer vision (encoding) and computer graphics (decoding) problems in signal transmission and reception. The creation of codec avatars require capture systems of unprecedented 3D sensing resolution, are also described.

Presenter

Yaser Sheikh

Facebook Reality Labs

Yaser Sheikh directs the Facebook Reality Lab in Pittsburgh, which is devoted to achieving photorealistic social interactions in AR and VR, and is an adjunct professor at Carnegie Mellon University. His research broadly focuses on machine perception and rendering of social behavior, spanning sub-disciplines in computer vision, computer graphics, and machine learning. With colleagues and students, he has won the Honda Initiation Award (2010), Popular Science’s "Best of What’s New" Award, best student paper award at CVPR (2018), best paper finalists at (CVPR 2019), best paper awards at WACV (2012), SAP (2012), SCA (2010), ICCV THEMIS (2009), best demo award at ECCV (2016), and he received the Hillman Fellowship for Excellence in Computer Science Research (2004). Yaser has served as a senior committee member at leading conferences in computer vision, computer graphics, and robotics including SIGGRAPH (2013, 2014), CVPR (2014, 2015, 2018), ICRA (2014, 2016), ICCP (2011), and served as an Associate Editor of CVIU. His research has been featured by various media outlets including The New York Times, BBC, MSNBC, Popular Science, and in technology media such as WIRED, The Verge, and New Scientist.