Learning to Importance Sample in Primary Sample Space. (7th June 2019)

• Record Type: Journal Article
• Authors: Zheng, Quan; Zwicker, Matthias
• Is Part Of: Computer graphics forum. Volume 38:Number 2(2019)
• Page Start: 169
• Page End: 179
• Publication Date: 2019-06-07
• Subjects: CCS Concepts -- Computing methodologies → Ray tracing -- Neural networks -- Importance sampling -- Global illumination; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.13628
• Languages: English
• ISSNs: 0167-7055

Abstract

Abstract: Importance sampling is one of the most widely used variance reduction strategies in Monte Carlo rendering. 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 primary sample space of the renderer using maximum likelihood estimation. We leverage a recent neural network architecture that was designed to represent real‐valued non‐volume preserving ("Real NVP") transformations in high dimensional spaces. We use Real NVP to non‐linearly warp primary sample space and obtain desired densities. In addition, Real NVP efficiently computes the determinant of the Jacobian of the warp, which is required to implement the change of integration variables implied by the warp. A main advantage of our approach is that it is agnostic of underlying light transport effects, and can be combined with an existing rendering technique by treating it as a black box. We show that our approach leads to effective variance reduction in several practical scenarios.