Generative Adversarial Networks for Non-Raytraced Global Illumination on Older GPU Hardware

TL;DR

This paper explores using GANs, specifically Pix2Pix, to generate high-quality global illumination images on older GPUs, offering a faster alternative to ray tracing with comparable visual quality.

Contribution

It demonstrates that GANs can effectively produce ray-traced quality images for global illumination on less powerful hardware, with detailed hyper-parameter settings and methodology.

Findings

GAN-generated images match ray-traced quality

Significant reduction in rendering time

Applicable to older GPU hardware

Abstract

We give an overview of the different rendering methods and we demonstrate that the use of a Generative Adversarial Networks (GAN) for Global Illumination (GI) gives a superior quality rendered image to that of a rasterisations image. We utilise the Pix2Pix architecture and specify the hyper-parameters and methodology used to mimic ray-traced images from a set of input features. We also demonstrate that the GANs quality is comparable to the quality of the ray-traced images, but is able to produce the image, at a fraction of the time.