Temporally Stable Metropolis Light Transport Denoising using Recurrent Transformer Blocks
Open Access
- 19 July 2024
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-14
Abstract
Metropolis Light Transport (MLT) is a global illumination algorithm that is well-known for rendering challenging scenes with intricate light paths. However, MLT methods tend to produce unpredictable correlation artifacts in images, which can introduce visual inconsistencies for animation rendering. This drawback also makes it challenging to denoise MLT renderings while maintaining temporal stability. We tackle this issue with modern learning-based methods and build a sequence denoiser combining the recurrent connections with the cutting-edge vision transformer architecture. We demonstrate that our sophisticated denoiser can consistently improve the quality and temporal stability of MLT renderings with difficult light paths. Our method is efficient and scalable for complex scene renderings that require high sample counts.Keywords
Funding Information
- NSF (2105806)
This publication has 38 references indexed in Scilit:
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows2021
- Real‐time Monte Carlo Denoising with Weight Sharing Kernel Prediction NetworkComputer Graphics Forum, 2021
- Neural Temporal Adaptive Sampling and DenoisingComputer Graphics Forum, 2020
- Stratified Markov Chain Monte Carlo Light TransportComputer Graphics Forum, 2020
- Multiple Axis‐Aligned Filters for Rendering of Combined Distribution EffectsComputer Graphics Forum, 2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Replica Exchange Light TransportComputer Graphics Forum, 2009
- Energy redistribution path tracingACM Transactions on Graphics, 2005
- A Simple and Robust Mutation Strategy for the Metropolis Light Transport AlgorithmComputer Graphics Forum, 2002
- A variance analysis of the Metropolis Light Transport algorithmComputers & Graphics, 2001