Gaussian Light Transport

We present a novel method for computing global illumination by expressing the solution to the light transport equation as a 13D Gaussian mixture model over positions, directions, surface normals and material properties. We show that including scene properties inside the Gaussian drastically reduces the number of functions needed and speeds up evaluation. As opposed to traditional light transport methods based on Neumann series, the parameters of our model are estimated directly by minimising the residual of the rendering equation.

While both optimisation and rendering require repeated evaluations of a linear combination of high-dimensional Gaussian functions, we introduce an efficient culling strategy that keeps the optimisation tractable and produces renderings in real time. Our representation yields fast, view-independent solutions to the light transport equation, with rendering times on the order of milliseconds and a fraction of the memory requirements of conventional neural rendering approaches.