Path‐based Monte Carlo Denoising Using a Three‐Scale Neural Network

Abstract

Monte Carlo rendering is widely used in the movie industry. Since it is costly to produce noise‐free results directly, Monte Carlo denoising is often applied as a post‐process. Recently, deep learning methods have been successfully leveraged in Monte Carlo denoising. They are able to produce high quality denoised results, even with very low sample rate, e.g. 4 spp (sample per pixel). However, for difficult scene configurations, some details could be blurred in the denoised results. In this paper, we aim at preserving more details from inputs rendered with low spp. We propose a novel denoising pipeline that handles three‐scale features ‐ pixel, sample and path ‐ to preserve sharp details, uses an improved Res2Net feature extractor to reduce the network parameters and a smooth feature attention mechanism to remove low‐frequency splotches. As a result, our method achieves higher denoising quality and preserves better details than the previous methods.

Real‐time Denoising Using BRDF Pre‐integration Factorization

“…They are able to denoise images rendered with pretty high sampling rate. Later, sample‐based approaches ([GLA∗19] and [LWY∗21]) further improve the denoising quality for renderings with low sampling rate, at the cost of both time and memory, which was later improved by Munkberg et al [MH20] via a layering embedding approach.…”