filename     : Zhan21a.pdf
entry        : inproceedings
conference   : Eurographics Symposium on Rendering
pages        : 1-13
year         : 2021
month        : June
title        : Deep Compositional Denoising for High-quality Monte Carlo Rendering
subtitle     :
author       : Xianyao Zhang, Marco Manzi, Thijs Vogels, Henrik Dahlberg, Markus Gross, Marios Papas
booktitle    : Computer Graphics Forum
ISSN/ISBN    : 1467-8659
editor       : Adrien Bousseau and Morgan McGuire
publisher    : The Eurographics Association and John Wiley & Sons Ltd.
publ.place   : Computer Graphics Forum
volume       : 40
issue        : 4
language     : English
keywords     : Denoising, Ray tracing
abstract     : We propose a deep-learning method for automatically decomposing noisy Monte Carlo renderings into components that kernel-predicting denoisers can denoise more effectively. In our model, a neural decomposition module learns to predict noisy components and corresponding feature maps, which are consecutively reconstructed by a denoising module. The components are predicted based on statistics aggregated at the pixel level by the renderer. Denoising these components individually allows the use of per-component kernels that adapt to each component's noisy signal characteristics. Experimentally, we show that the proposed decomposition module consistently improves the denoising quality of current state-of-the-art kernel-predicting denoisers on large-scale academic and production datasets.