Inverse Transform Sampling Using Ray Tracing Hardware

Abstract

Accurate radiance estimates of high dynamic range textures require importance sampling to direct rays toward influential regions. However, traditional inverse transform sampling involves several expensive searches to locate these highly influential pixels. We propose a reformulation of inverse transform sampling that replaces these texture space searches with a single hardware-accelerated ray traversal search using cumulative probability geometry. We evaluate the performance and scalability of our approach on a set of emissive dome light textures and demonstrate significant improvements over traditional solutions.