Real-time Monte Carlo Denoising with the Neural Bilateral Grid

Simple item page
dc.contributor.authorMeng, Xiaoxuen_US
dc.contributor.authorZheng, Quanen_US
dc.contributor.authorVarshney, Amitabhen_US
dc.contributor.authorSingh, Gurpriten_US
dc.contributor.authorZwicker, Matthiasen_US
dc.contributor.editorDachsbacher, Carsten and Pharr, Matten_US
dc.date.accessioned2020-06-28T15:27:26Z
dc.date.available2020-06-28T15:27:26Z
dc.date.issued2020
dc.description.abstractReal-time denoising for Monte Carlo rendering remains a critical challenge with regard to the demanding requirements of both high fidelity and low computation time. In this paper, we propose a novel and practical deep learning approach to robustly denoise Monte Carlo images rendered at sampling rates as low as a single sample per pixel (1-spp). This causes severe noise, and previous techniques strongly compromise final quality to maintain real-time denoising speed. We develop an efficient convolutional neural network architecture to learn to denoise noisy inputs in a data-dependent bilateral space. Our neural network learns to generate a guide image for first splatting noisy data into the grid, and then slicing it to read out the denoised data. To seamlessly integrate bilateral grids into our trainable denoising pipeline, we leverage a differentiable bilateral grid, called neural bilateral grid, which enables end-to-end training. In addition, we also show how we can further improve denoising quality using a hierarchy of multi-scale bilateral grids. Our experimental results demonstrate that this approach can robustly denoise 1-spp noisy input images at real-time frame rates (a few milliseconds per frame). At such low sampling rates, our approach outperforms state-of-the-art techniques based on kernel prediction networks both in terms of quality and speed, and it leads to significantly improved quality compared to the state-of-the-art feature regression technique.en_US
dc.description.sectionheadersDenoising and Filtering
dc.description.seriesinformationEurographics Symposium on Rendering - DL-only Track
dc.identifier.doi10.2312/sr.20201133
dc.identifier.isbn978-3-03868-117-5
dc.identifier.issn1727-3463
dc.identifier.pages13-24
dc.identifier.urihttps://doi.org/10.2312/sr.20201133
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/sr20201133
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.subjectRay tracing
dc.titleReal-time Monte Carlo Denoising with the Neural Bilateral Griden_US
Files
Original bundle
Now showing 1 - 4 of 4
Thumbnail Image
Name:
013-024.pdf
Size:
92.47 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
real_time_monte_carlo_denoising_with_the_neural_bilateral_grid_egsr_supplementary_prepress.pdf
Size:
10.13 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
datapackage-egsr1036.zip
Size:
264.83 MB
Format:
Zip file
Download
No Thumbnail Available
Name:
neuralbilateralgrid_v2.mp4
Size:
219.04 MB
Format:
Unknown data format
Download
Collections
Rendering 2020 - DL-only Track