Bayesian Collaborative Denoising for Monte Carlo Rendering

Malik Boughida and Tamy Boubekeur
EGSR 2017 - Computer Graphics Forum

Bayesian Collaborative Denoising


The stochastic nature of Monte Carlo rendering algorithms inherently produces noisy images. Essentially, three approaches have been developed to solve this issue: improving the ray-tracing strategies to reduce pixel variance, providing adaptive sampling by increasing the number of rays in regions needing so, and filtering the noisy image as a post-process. Although the algorithms from the latter category introduce bias, they remain highly attractive as they quickly improve the visual quality of the images, are compatible with all sorts of rendering effects, have a low computational cost and, for some of them, avoid deep modifications of the rendering engine.

In this paper, we build upon recent advances in both non-local and collaborative filtering methods to propose a new efficient denoising operator for Monte Carlo rendering. Starting from the local statistics which emanate from the pixels sample distribution, we enrich the image with local covariance measures and introduce a non-local bayesian filter which is specifically designed to address the noise stemming from Monte Carlo rendering. The resulting algorithm only requires the rendering engine to provide for each pixel a histogram and a covariance matrix of its color samples. Compared to state-of-the-art sample-based methods, we obtain improved denoising results, especially in dark areas, with a large increase in speed and more robustness with respect to the main parameter of the algorithm. We provide a detailed mathematical exposition of our bayesian approach, discuss extensions to multiscale execution, adaptive sampling and animated scenes, and experimentally validate it on a collection of scenes.


Related publications

Interactive Comparison

museum-monkey sponza-dir sibenik-car

Note: javascript base code taken from the Deep Shading project page.


 author = {Malik Boughida and Tamy Boubekeur},
 title = {Bayesian Collaborative Denoising for Monte Carlo Rendering},
 journal = {Computer Graphics Forum (Proc. EGSR 2017)},
 volume = {36},
 number = {4},
 pages = {137--153},
 year = {2017}