Get the latest tech news
Radiant Foam: Real-Time Differentiable Ray Tracing
Shrisudhan Govindarajan*1, Daniel Rebain*2, Kwang Moo Yi2, Andrea Tagliasacchi1,3,4 1Simon Fraser University, 2University of British Columbia, 3University of Toronto, 4Google Deepmind * denotes equal contribution Research on differentiable scene representations is consistently moving towards more efficient, real-time models. Recently, this has led to the popularization of splatting methods, which eschew the traditional ray-based rendering of radiance fields in favor of rasterization.
Recently, this has led to the popularization of splatting methods, which eschew the traditional ray-based rendering of radiance fields in favor of rasterization. Our method also avoids the challenges typically associated with optimizing a discrete mesh, as the cell boundaries of the Voronoi diagram vary continuously with changes in the positions of sites. BibTeX@article{govindarajan2025radfoam, author = {Govindarajan, Shrisudhan and Rebain, Daniel and Yi, Kwang Moo and Tagliasacchi, Andrea}, title = {Radiant Foam: Real-Time Differentiable Ray Tracing}, journal = {arXiv:2502.01157}, year = {2025}, }
Or read this on Hacker News
