Wavelet Representation and Sampling of Complex Luminaires

Abstract

We contribute a technique for rendering the illumination of complex luminaires based on wavelet-compressed light fields while the direct appearance of the luminaire is handled with previous techniques. During a brief photon tracing phase, we pre-compute the radiance field of the luminaire. Then, we employ a compression scheme which is designed to facilitate fast per-ray run-time reconstructions of the field and importance sampling. To treat aliasing, we propose a two-component filtering solution: a 4D Gaussian filter during the pre-computation stage and a 4D stochastic Gaussian filter during rendering. We have developed an importance sampling strategy based on providing an initial guess from low-resolution and low-memory viewpoint samplers that is subsequently refined by a hierarchical process over the wavelet frequency bands. Our technique is straightforward to integrate in rendering systems and has all the features that make it practical for production renderers — MIS compatibility, brief pre-computation, low memory requirements, and efficient field evaluation and importance sampling.