Advances in Neural Rendering

SIGGRAPH 2021 Course

Welcome to the SIGGRAPH 2021 course on Advances in Neural Rendering! The webpage for the CVPR 2020 tutorial can be found here.

How to participate?

SIGGRAPH 2021 has concluded. The recorded talks are now available on YouTube:

What is Neural Rendering?

Neural rendering is an emerging class of deep image and video generation approaches that enable control of scene properties such as illumination, camera parameters, pose, geometry, appearance, and semantic structure. It combines machine learning techniques with physical knowledge from computer graphics to obtain controllable and photo-realistic models of scenes.

What will I learn in this course?

This course covers the advances in neural rendering over the last year. We will first cover the fundamentals of machine learning and computer graphics relevant for neural rendering. Next, we will present state of the art techniques for the many important neural rendering methods for applications such as novel view synthesis, semantic photo manipulation, facial and body reenactment, relighting, free-viewpoint video, and the creation of photo-realistic avatars for virtual and augmented reality telepresence. Finally, we will conclude with a discussion on the ethical implications of this technology and open research problems.

Contents

Topic Speaker
Introduction
Fundamentals Michael Zollhöfer
Generative Adversarial Networks
Loss Functions Jun-Yan Zhu
GANs with 3D Control Ayush Tewari
Neural Scene Representations
Neural Scene Representations Gordon Wetzstein
Novel View Synthesis for Objects and Scenes
Introduction Vincent Sitzmann
Neural Volumetric Rendering Ben Mindenhall
Fast Rendering of NeRFs Lingjie Liu
Towards Instant 3D Capture Dan Goldman
Deformable NeRFs Keunhong Park
Learning to Relight
Relightable and Editable Neural Rendering Zexiang Xu
Total Relighting Sergio Orts-Escolano
Relightable NeRFs Pratul Srinivasan
Compositional Scene Representations
Compositional Scene Representations Michelle Guo
Free Viewpoint Videos
Overview of NeRFs for General Dynamic Scenes Edgar Tretschk
Efficient Neural Rendering of Dynamic Humans and Scenes Stephen Lombardi
Neural Rendering for Dynamic Performance Capture Rohit Pandey
Facial and Body Rendering
Neural Rendering of Faces and Bodies Justus Thies
Neural Rendering and Video-based Animation of Human Actors Christian Theobalt
Neural Rendering for Animatable Avatars Tomas Simon
Conclusion
Open Challenges Ohad Fried
Discussion on Ethical Implications (only live) Maneesh Agrawala

Organizing team

Ayush Tewari, Ohad Fried, Justus Thies, Michael Zollhöfer.

Location & time

August 9th, 2021, 9:00 PT.
SIGGRAPH 2021 is a virtual conference.