Torsten Sattler
Czech Technical University
SUN 13:30 – 15:00
Neural Radiance Fields (NeRFs) represent the appearance and geometry of scene as an implicit function, stored in the weights of a neural network. They are trained from images with known camera intrinsics and extrinsics, without necessarily having any information about the 3D structure of the scene (although having information about the 3D structure of the scene can help during training). NeRFs are rapidly gaining in popularity due to their ability to produce photo-realistic renderings of scene from novel viewpoints. In particular, they are able to precisely model view-dependent effects such as reflections and refractions. This tutorial gives a brief introduction into Neural Radiance Fields, discussing the original formulation as well as selected state-of-the-art variants. In addition, we will have a brief look at modern NeRF software packages.
 Dr. Torsten Sattler, CIIRC CTU, PRAHA Torsten Sattler is a Senior Researcher at Czech Technical University in Prague. Before, he was a tenured associate professor at Chalmers University of Technology. He received a PhD in Computer Science from RWTH Aachen University, Germany, in 2014. From December 2013 to December 2018, he was a post-doctoral and senior researcher at ETH Zurich. Torsten has extensively worked on feature-based localization methods, long-term localization (see also the benchmarks at visuallocalization.net), localization on mobile devices, learning local features, and using semantic scene understanding for localization. Recently, his group started focusing on neural radiance fields and other neural scene representations. Torsten has co-organized tutorials and workshops at CVPR, ECCV, and ICCV, and was / is an area chair for CVPR, ICCV, 3DV, GCPR, ICRA, and ECCV. He was a program chair for DAGM GCPR’20, a general chair for 3DV’22, and will be a program chair for ECCV’24. |