Gaussian Light Transport: 13D Gaussian Mixtures Speed Up Global Illumination
ssh4net · x · 2026-09-11
Researchers from INRIA, Grenoble University and the University of Edinburgh present Gaussian Light Transport, expressing the light transport equation's solution as a 13D Gaussian mixture over positions, directions, surface normals and material properties. Including scene properties in the Gaussian representation drastically reduces the number of basis functions and speeds up evaluation. Unlike traditional Neumann-series methods, parameters are directly estimated by minimizing the rendering equation residual. Paper and project page are live; code coming soon.
More from Research
- Four-Color Theorem Gets a Rare New Proof, Revisiting Its Controversial 1970s Computer-Assisted Solution — soumitrashukla9 · 2026-09-11
- The Roadmap of Mathematics for Machine Learning: Linear Algebra, Calculus, Probability — TivadarDanka · 2026-09-11
- GEVIBench launches as a comprehensive benchmark for comparing voltage indicators — drmichaellevin · 2026-09-11
- Llama Loves Pirates — Goodfire's Tom McGrath on teaching math without the pirate style — Machine Learning Street Talk · 2026-09-11
- Fortnow: P vs NP beyond AI's reach, but NP vs L separations could fall — fortnow · 2026-09-11
- MaP-WAM tackles non-Markovian robot manipulation with memory-grounded planning — Sizhe Zhao · 2026-09-11