Self-Supervised Neural Global Illumination for Stereo-Rendering

Simple item page
dc.contributor.authorZhang, Ziyangen_US
dc.contributor.authorSimo-Serra, Edgaren_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorHan, Ping-Hsuanen_US
dc.contributor.editorLin, Shih-Syunen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorSchneider, Teseoen_US
dc.contributor.editorTsai, Hsin-Rueyen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.contributor.editorZhang, Eugeneen_US
dc.date.accessioned2025-10-07T06:05:13Z
dc.date.available2025-10-07T06:05:13Z
dc.date.issued2025
dc.description.abstractWe propose a novel neural global illumination baking method for real-time stereoscopic rendering, with applications to virtual reality. Naively, applying neural global illumination to stereoscopic rendering requires running the model per eye, which doubles the computational cost making it infeasible for real-time virtual reality applications. Training a stereoscopic model from scratch is also impractical, as it will require additional path tracing ground truth for both eyes. We overcome these limitations by first training a common neural global illumination baking model using a single eye dataset. We then use self-supervised learning to train a second stereoscopic model using the first model as a teacher model, where we also transfer the weights of the first model to the second model to accelerate the training process. Furthermore, our spatial coherence loss encourages consistency between the rendering for two eyes. Experiments show our method achieves the same quality as the original single-eye model with minimal overhead, enabling real-time performance in virtual reality.en_US
dc.description.sectionheadersPosters and Demos
dc.description.seriesinformationPacific Graphics Conference Papers, Posters, and Demos
dc.identifier.doi10.2312/pg.20251305
dc.identifier.isbn978-3-03868-295-0
dc.identifier.pages2 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20251305
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20251305
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 → Rendering; Neural networks; Human-centered computing → Virtual reality
dc.subjectComputing methodologies → Rendering
dc.subjectNeural networks
dc.subjectHuman centered computing → Virtual reality
dc.titleSelf-Supervised Neural Global Illumination for Stereo-Renderingen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pg20251305.pdf
Size:
7.18 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2025 Conference Papers, Posters, and Demos