Abstract

Gradient-domain rendering accelerates realistic image synthesis by also estimating pixel color differences, which helps reconstruct high frequencies in the image domain. Converged images still require many samples per pixel even with denoising, and to this date, no real-time gradient-domain rendering methods have been proposed. We enable gradient-domain methods in real-time rendering by spatiotemporal sample reuse with a novel path space extension in gradient image rendering.

We further explore this concept by implementing ReSTIR G-PT, ReSTIR gradient-domain path tracing, and find that relative sparsity of the gradient image allows highly selective spatial reuse and real-time frame rates. Our method outperforms the baseline methods visually and statistically.