Fast Local Neural Regression for Low-Cost, Path Traced Lambertian Global Illumination

TL;DR

This paper introduces a fast, low-cost neural denoising method for real-time path traced Lambertian global illumination, achieving high-quality results at very low sample counts on commodity hardware.

Contribution

It presents a neural-enhanced local linear model denoiser that is computationally efficient, improves existing denoising quality, and extends to joint denoising and upsampling using guide channels.

Findings

Faithful single-frame global illumination reconstruction at 1 spp

Enhanced denoising quality with simplified mathematical model

Effective use of ambient occlusion as a guide channel

Abstract

Despite recent advances in hardware acceleration of ray tracing, real-time ray budgets remain stubbornly limited at a handful of samples per pixel (spp) on commodity hardware, placing the onus on denoising algorithms to achieve high visual quality for path traced global illumination. Neural network-based solutions give excellent result quality at the cost of increased execution time relative to hand-engineered methods, making them less suitable for deployment on resource-constrained systems. We therefore propose incorporating a neural network into a computationally-efficient local linear model-based denoiser, and demonstrate faithful single-frame reconstruction of global illumination for Lambertian scenes at very low sample counts (1spp) and for low computational cost. Other contributions include improving the quality and performance of local linear model-based denoising through a simplified mathematical treatment, and demonstration of the surprising usefulness of ambient occlusion as a guide channel. We also show how our technique is straightforwardly extensible to joint denoising and upsampling of path traced renders with reference to low-cost, rasterized guide channels.