no code implementations • 10 Jun 2024 • Xiaoming Zhao, Pratul P. Srinivasan, Dor Verbin, Keunhong Park, Ricardo Martin Brualla, Philipp Henzler
Existing methods for relightable view synthesis -- using a set of images of an object under unknown lighting to recover a 3D representation that can be rendered from novel viewpoints under a target illumination -- are based on inverse rendering, and attempt to disentangle the object geometry, materials, and lighting that explain the input images.
no code implementations • CVPR 2024 • Rundi Wu, Ben Mildenhall, Philipp Henzler, Keunhong Park, Ruiqi Gao, Daniel Watson, Pratul P. Srinivasan, Dor Verbin, Jonathan T. Barron, Ben Poole, Aleksander Holynski
3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at rendering photorealistic novel views of complex scenes.
no code implementations • 21 Aug 2023 • Keunhong Park, Philipp Henzler, Ben Mildenhall, Jonathan T. Barron, Ricardo Martin-Brualla
We propose using a proxy problem to compute a whitening transform that eliminates the correlation between camera parameters and normalizes their effects, and we propose to use this transform as a preconditioner for the camera parameters during joint optimization.
2 code implementations • 24 Jun 2021 • Keunhong Park, Utkarsh Sinha, Peter Hedman, Jonathan T. Barron, Sofien Bouaziz, Dan B Goldman, Ricardo Martin-Brualla, Steven M. Seitz
A common approach to reconstruct such non-rigid scenes is through the use of a learned deformation field mapping from coordinates in each input image into a canonical template coordinate space.
no code implementations • 17 Apr 2021 • Christopher Xie, Keunhong Park, Ricardo Martin-Brualla, Matthew Brown
We investigate the use of Neural Radiance Fields (NeRF) to learn high quality 3D object category models from collections of input images.
2 code implementations • ICCV 2021 • Keunhong Park, Utkarsh Sinha, Jonathan T. Barron, Sofien Bouaziz, Dan B Goldman, Steven M. Seitz, Ricardo Martin-Brualla
We present the first method capable of photorealistically reconstructing deformable scenes using photos/videos captured casually from mobile phones.
1 code implementation • CVPR 2020 • Keunhong Park, Arsalan Mousavian, Yu Xiang, Dieter Fox
We evaluate the performance of our method for unseen object pose estimation on MOPED as well as the ModelNet and LINEMOD datasets.
1 code implementation • 26 Sep 2018 • Keunhong Park, Konstantinos Rematas, Ali Farhadi, Steven M. Seitz
Existing online 3D shape repositories contain thousands of 3D models but lack photorealistic appearance.