Neural Denoising for Spectral Monte Carlo Rendering

Simple item page
dc.contributor.authorRouphael, Robinen_US
dc.contributor.authorNoizet, Mathieuen_US
dc.contributor.authorPrévost, Stéphanieen_US
dc.contributor.authorDeleau, Hervéen_US
dc.contributor.authorSteffenel, Luiz-Angeloen_US
dc.contributor.authorLucas, Laurenten_US
dc.contributor.editorSauvage, Basileen_US
dc.contributor.editorHasic-Telalovic, Jasminkaen_US
dc.date.accessioned2022-04-22T07:54:28Z
dc.date.available2022-04-22T07:54:28Z
dc.date.issued2022
dc.description.abstractSpectral Monte Carlo (MC) rendering is still to be largely adopted partially due to the specific noise, called color noise, induced by wavelength-dependent phenomenons. Motivated by the recent advances in Monte Carlo noise reduction using Deep Learning, we propose to apply the same approach to color noise. Our implementation and training managed to reconstruct a noise-free output while conserving high-frequency details despite a loss of contrast. To address this issue, we designed a three-step pipeline using the contribution of a secondary denoiser to obtain high-quality results.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationEurographics 2022 - Posters
dc.identifier.doi10.2312/egp.20221011
dc.identifier.isbn978-3-03868-171-7
dc.identifier.issn1017-4656
dc.identifier.pages25-26
dc.identifier.pages2 pages
dc.identifier.urihttps://doi.org/10.2312/egp.20221011
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/egp20221011
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies --> Ray tracing; Neural networks; Image processing
dc.subjectComputing methodologies
dc.subjectRay tracing
dc.subjectNeural networks
dc.subjectImage processing
dc.titleNeural Denoising for Spectral Monte Carlo Renderingen_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
025-026.pdf
Size:
13.6 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
poster1016_poster_pdf.pdf
Size:
643.74 KB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
poster1016_video.mp4
Size:
59.69 MB
Format:
Unknown data format
Download
Collections
EG 2022 - Posters