A machine learning approach for filtering Monte Carlo noise
- 27 July 2015
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 34 (4), 1-12
- https://doi.org/10.1145/2766977
Abstract
The most successful approaches for filtering Monte Carlo noise use feature-based filters (e.g., cross-bilateral and cross non-local means filters) that exploit additional scene features such as world positions and shading normals. However, their main challenge is finding the optimal weights for each feature in the filter to reduce noise but preserve scene detail. In this paper, we observe there is a complex relationship between the noisy scene data and the ideal filter parameters, and propose to learn this relationship using a nonlinear regression model. To do this, we use a multilayer perceptron neural network and combine it with a matching filter during both training and testing. To use our framework, we first train it in an offline process on a set of noisy images of scenes with a variety of distributed effects. Then at run-time, the trained network can be used to drive the filter parameters for new scenes to produce filtered images that approximate the ground truth. We demonstrate that our trained network can generate filtered images in only a few seconds that are superior to previous approaches on a wide range of distributed effects such as depth of field, motion blur, area lighting, glossy reflections, and global illumination.Keywords
This publication has 43 references indexed in Scilit:
- Temporal light field reconstruction for rendering distribution effectsACM Transactions on Graphics, 2011
- Guided Image Filtering for Interactive High‐quality Global IlluminationComputer Graphics Forum, 2011
- Progressive Expectation-Maximization for Hierarchical Volumetric Photon MappingComputer Graphics Forum, 2011
- Adaptive wavelet renderingACM Transactions on Graphics, 2009
- Shadowing Dynamic Scenes with Arbitrary BRDFsComputer Graphics Forum, 2009
- Multidimensional adaptive sampling and reconstruction for ray tracingACM Transactions on Graphics, 2008
- Efficient BRDF importance sampling using a factored representationACM Transactions on Graphics, 2004
- Anisotropic diffusion for Monte Carlo noise reductionACM Transactions on Graphics, 1999
- Distributed ray tracingACM SIGGRAPH Computer Graphics, 1984
- Estimation of the Mean of a Multivariate Normal DistributionThe Annals of Statistics, 1981