Estimation of Global Illumination using Cycle-Consistent Adversarial Networks

Simple item page
dc.contributor.authorOh, Junhoen
dc.contributor.authorAbbott, A. Lynnen
dc.date.accessioned2025-03-05T15:31:45Zen
dc.date.available2025-03-05T15:31:45Zen
dc.date.issued2024-10-15en
dc.description.abstractSynthesis of realistic virtual environments requires careful rendering of light and shadows, a task often bottle-necked by the high computational cost of global illumination (GI) techniques. This paper introduces a new GI approach that improves computational efficiency without a significant reduction in image quality. The proposed system transforms initial direct-illumination renderings into globally illuminated representations by incorporating a Cycle-Consistent Adversarial Network (CycleGAN). Our CycleGAN-based approach has demonstrated superior performance over the Pix2Pix model according to the LPIPS metric, which emphasizes perceptual similarity. To facilitate such comparisons, we have created a novel dataset (to be shared with the research community) that provides in-game images that were obtained with and without GI rendering. This work aims to advance real-time GI estimation without the need for costly, specialized computational hardware. Our work and the dataset are made publicly available at https://github.com/junhofive/CycleGAN-Illumination.en
dc.description.notesYes, full paper (Peer reviewed?)en
dc.format.extentPages 73-86en
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.1007/978-3-031-77392-1_6en
dc.identifier.eissn1611-3349en
dc.identifier.issn0302-9743en
dc.identifier.orcidAbbott, Amos [0000-0003-3850-6771]en
dc.identifier.urihttps://hdl.handle.net/10919/124800en
dc.identifier.volume15046en
dc.language.isoenen
dc.publisherSpringeren
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectVirtual Realityen
dc.subjectVideo Gamesen
dc.subjectGraphicsen
dc.subjectLightingen
dc.subjectGlobal Illuminationen
dc.subjectGANen
dc.subjectCycleGANen
dc.titleEstimation of Global Illumination using Cycle-Consistent Adversarial Networksen
dc.title.serialLecture Notes in Computer Scienceen
dc.typeConference proceedingen
dc.type.dcmitypeTexten
pubs.organisational-groupVirginia Techen
pubs.organisational-groupVirginia Tech/Engineeringen
pubs.organisational-groupVirginia Tech/Engineering/Electrical and Computer Engineeringen
pubs.organisational-groupVirginia Tech/All T&R Facultyen
pubs.organisational-groupVirginia Tech/Engineering/COE T&R Facultyen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Oh - Abbott - Estimation of Global Illumination.pdf
Size:
9.72 MB
Format:
Adobe Portable Document Format
Description:
Accepted version
Download
License bundle
Now showing 1 - 1 of 1
Name:
license.txt
Size:
1.5 KB
Format:
Plain Text
Description:
Download

Collections

All Faculty Deposits
Scholarly Works, Electrical and Computer Engineering