Ensemble Denoising for Monte Carlo Renderings

Various denoising methods have been proposed to clean up the noise in Monte Carlo (MC) renderings, each having different advantages, disadvantages, and applicable scenarios. In this paper, we present Ensemble Denoising, an optimization-based technique that combines multiple individual MC denoisers. The combined image is modeled as a per-pixel weighted sum of output images from the individual denoisers. Computation of the optimal weights is formulated as a constrained quadratic programming problem, where we apply a dual-buffer strategy to estimate the overall MSE. We further propose an iterative solver to overcome practical issues involved in the optimization. Besides nice theoretical properties, our ensemble denoiser is demonstrated to be effective and robust, and outperforms any individual denoiser across dozens of scenes and different levels of sample rates. We also perform a comprehensive analysis on the selection of individual denoisers to be combined, providing important and practical guides for users.

Automated summary

This paper introduces an optimization-based ensemble denoising technique that combines multiple individual MC denoisers to clean up noise in renderings. The method computes optimal weights for combining output images from individual denoisers, and is shown to be effective and robust across various scenes and sample rates, outperforming individual denoisers. Additionally, a comprehensive analysis on selecting denoisers to be combined is provided for practical guidance.