Neural Importance Sampling

by   Thomas Müller, et al.

We propose to use deep neural networks for generating samples in Monte Carlo integration. Our work is based on non-linear independent component analysis, which we extend in numerous ways to improve performance and enable its application to integration problems. First, we introduce piecewise-polynomial coupling transforms that greatly increase the modeling power of individual coupling layers. Second, we propose to preprocess the inputs of neural networks using one-blob encoding, which stimulates localization of computation and improves inference. Third, we derive a gradient-descent-based optimization for the KL and the χ^2 divergence for the specific application of Monte Carlo integration with stochastic estimates of the target distribution. Our approach enables fast and accurate inference and efficient sample generation independent of the dimensionality of the integration domain. We demonstrate the benefits of our approach for generating natural images and in two applications to light-transport simulation. First, we show how to learn joint path-sampling densities in primary sample space and how to importance sample multi-dimensional path prefixes thereof. Second, we use our technique to extract conditional directional densities driven by the triple product of the rendering equation, and leverage them for path guiding. In all applications, our approach yields on-par or higher performance at equal sample count than competing techniques.


Learning to Importance Sample in Primary Sample Space

Importance sampling is one of the most widely used variance reduction st...

Primary-Space Adaptive Control Variates using Piecewise-Polynomial Approximations

We present an unbiased numerical integration algorithm that handles both...

Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks

We present a technique for efficiently synthesizing images of atmospheri...

Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising

Recent advances in differentiable rendering have enabled high-quality re...

Neural Classifiers based Monte Carlo simulation

Acceptance-rejection (AR), Independent Metropolis Hastings (IMH) or impo...

Path Throughput Importance Weights

Many Monte Carlo light transport simulations use multiple importance sam...

Perturbation-Assisted Sample Synthesis: A Novel Approach for Uncertainty Quantification

This paper introduces a novel generator called Perturbation-Assisted Sam...

Please sign up or login with your details

Forgot password? Click here to reset