Neural Implicit Representations for 3D Vision and Beyond by Dr. Andreas Geiger @QUVA

Title: Neural Implicit Representations for 3D Vision and Beyond

Content
00:00 - Introduction
01:25 - Implicit Neural Representations
21:39 - Differentiable Volume Rendering
30:16 - Neural Radiance Fields
34:44 - Generative Radiance Fields
42:29 - Further Applications
48:05 - Summary
49:40 - Q&A


Abstract: In this talk, Andreas Geiger will show several recent results of his group on learning neural implicit 3D representations, departing from the traditional paradigm of representing 3D shapes explicitly using voxels, point clouds or meshes. Implicit representations have a small memory footprint and allow for modelling any 3D topology at arbitrary resolution in continuous function space. He will show the ability and limitations of these approaches in the context of reconstructing 3D geometry, texture and motion. He will further demonstrate a technique for learning implicit 3D models using only 2D supervision through implicit differentiation of the level set constraint. Andreas will close with some applications from various domains including large-scale reconstruction, real-time novel view synthesis, generative modelling, human body estimation, and self-driving.

Bio: Andreas Geiger is professor at the University of Tübingen and group leader at the Max Planck Institute for Intelligent Systems. Prior to this, he was a visiting professor at ETH Zürich and a research scientist at MPI-IS. He studied at KIT, EPFL and MIT and received his PhD degree in 2013 from the KIT. His research interests are at the intersection of 3D reconstruction, motion estimation, scene understanding and sensory-motor control. He maintains the KITTI vision benchmark and coordinates the ELLIS PhD and PostDoc program.

[hopbunny]

Nice talk! By the way, is there any places to download the slides? Thanks~