Keynotes
Niloy Mitra: Neural Surface Maps
Abstract: TBD
Bio: Niloy J. Mitra leads the Smart Geometry Processing group in the Department of Computer Science at University College London and also heads the Adobe Research London Lab. He received his PhD from Stanford University under the guidance of Leonidas Guibas. His current research focuses on developing machine learning frameworks for generating high-quality geometric and appearance models for CG applications. Niloy received the 2019 Eurographics Outstanding Technical Contributions Award, the 2015 British Computer Society Roger Needham Award, and the 2013 ACM Siggraph Significant New Researcher Award. For more details, please visit http://geometry.cs.ucl.ac.uk/index.php. Besides research, Niloy is an active DIYer and loves reading, bouldering, and cooking.
Angjoo Kanazawa: Real-time Rendering of NeRFs with PlenOctrees
Abstract: TBD
Bio: Angjoo Kanazawa is an Assistant Professor in the Department of Electrical Engineering and Computer Science at the University of California at Berkeley. Previously, she was a research scientist at Google NYC with Noah Snavely and prior to that she was a BAIR postdoc at UC Berkeley advised by Jitendra Malik, Alyosha Efros, and Trevor Darrell. She completed her PhD in CS at the University of Maryland, College Park with her advisor David Jacobs. She has also spent time at the Max Planck Institute for Intelligent Systems with Michael Black. Her research is at the intersection of computer vision, graphics, and machine learning, focusing on visual perception of the dynamic 3D world behind everyday photographs and video.
Justin Solomon: Geometry Processing-Inspired Deep Learning
Abstract: The discipline of geometry processing has developed mature tools for modeling, editing, and understanding surfaces embedded in 3D, incorporating ideas from differential geometry, numerical simulation, and other mathematical fields. Despite the mature geometry processing toolbox, thanks to limitations of current architectures, deep learning algorithms for processing geometric data have little in common with standard geometry processing algorithmic design principles. In this talk, I will show how we can develop sensible algorithms for deep learning from shapes built using standard operations in geometry processing, yielding top-performing learning methods that fit seamlessly into existing workflows.
Bio: Justin Solomon is an associate professor of Electrical Engineering and Computer Science at MIT. He directs the Geometric Data Processing Group in the MIT Computer Science and Artificial Intelligence Laboratory, which studies problems at the intersection of geometry, optimization, and applications like graphics, vision, and learning.