Learning to Importance Sample in Primary Sample Space

arXiv:1808.07840v2 Announce Type: replace
Abstract: Importance sampling is one of the most widely used variance reduction strategies in Monte Carlo rendering. In this paper, we propose a novel importance sampling technique that uses a neural network to learn how to sample from a desired density represented by a set of samples. Our approach considers an existing Monte Carlo rendering algorithm as a black box. During a scene-dependent training phase, we learn to generate samples with a desired density in the …

abstract arxiv cs.gr cs.lg importance learn network neural network novel paper rendering sample samples sampling set space stat.ml strategies type variance