no code implementations • 13 Feb 2024 • Michael Fischer, Zhengqin Li, Thu Nguyen-Phuoc, Aljaz Bozic, Zhao Dong, Carl Marshall, Tobias Ritschel
A Neural Radiance Field (NeRF) encodes the specific relation of 3D geometry and appearance of a scene.
no code implementations • 12 Sep 2023 • Sayantan Datta, Carl Marshall, Derek Nowrouzezahrai, Zhao Dong, Zhengqin Li
We introduce differentiable indirection -- a novel learned primitive that employs differentiable multi-scale lookup tables as an effective substitute for traditional compute and data operations across the graphics pipeline.
no code implementations • ICCV 2023 • Cheng Sun, Guangyan Cai, Zhengqin Li, Kai Yan, Cheng Zhang, Carl Marshall, Jia-Bin Huang, Shuang Zhao, Zhao Dong
In the last stage, initialized by the neural predictions, we perform PBIR to refine the initial results and obtain the final high-quality reconstruction of object shape, material, and illumination.
Ranked #1 on Depth Prediction on Stanford-ORB