Input-Dependent Uncorrelated Weighting for Monte Carlo Denoising

Jonghee Back 1 , Binh-Son Hua 2 , Toshiya Hachisuka 3 , Bochang Moon 1

GIST 1 , Trinity College Dublin 2 , University of Waterloo 3

ACM SIGGRAPH Asia 2023 Conference Proceedings

Input-Dependent Uncorrelated Weighting for Monte Carlo Denoising
Our denoising with a new input-dependent kernel locally weights the two input pixel estimates, path tracing with independent sampling (b) and common random numbers (CRN) (c) to produce a denoised output while preventing image edges from blurring (i.e., a limited denoising bias). The numerical accuracy is measured by a relative L2 error using the reference images (a) and (e).


Image-space denoising techniques have been widely employed in Monte Carlo rendering, typically blending neighboring pixel estimates using a denoising kernel. It is widely recognized that a kernel should be adapted to characteristics of the input pixel estimates in order to ensure robustness to diverse image features and amount of noise. Denoising with such an input-dependent kernel, however, can introduce a bias that makes the denoised estimate even less accurate than the noisy input estimate. Consequently, it has been considered essential to balance the bias introduced by denoising and the reduction of noise. We propose a new framework to define an input-dependent kernel that departs from the existing approaches based on error estimation or supervised learning. Rather than seeking an optimal bias-noise balance as in those existing approaches, we propose to constrain the amount of bias introduced by denoising. Such a constraint is made possible by the concept of uncorrelated statistics, which has never been applied for denoising. By designing an input-dependent kernel with uncorrelated weights against the input pixel estimates, our denoising kernel can reduce data-dependent noise with a negligible amount of bias in most cases. We demonstrate the effectiveness of our method for various scenes.