An evaluation of SVBRDF Prediction from Generative Image Models for Appearance Modeling of 3D Scenes

Simple item page
dc.contributor.authorGauthier, Albanen_US
dc.contributor.authorDeschaintre, Valentinen_US
dc.contributor.authorLanvin, Alexandreen_US
dc.contributor.authorDurand, Fredoen_US
dc.contributor.authorBousseau, Adrienen_US
dc.contributor.authorDrettakis, Georgeen_US
dc.contributor.editorWang, Beibeien_US
dc.contributor.editorWilkie, Alexanderen_US
dc.date.accessioned2025-06-20T07:49:21Z
dc.date.available2025-06-20T07:49:21Z
dc.date.issued2025
dc.description.abstractDigital content creation is experiencing a profound change with the advent of deep generative models. For texturing, conditional image generators now allow the synthesis of realistic RGB images of a 3D scene that align with the geometry of that scene. For appearance modeling, SVBRDF prediction networks recover material parameters from RGB images. Combining these technologies allows us to quickly generate SVBRDF maps for multiple views of a 3D scene, which can be merged to form a SVBRDF texture atlas of that scene. In this paper, we analyze the challenges and opportunities for SVBRDF prediction in the context of such a fast appearance modeling pipeline. On the one hand, single-view SVBRDF predictions might suffer from multiview incoherence and yield inconsistent texture atlases. On the other hand, generated RGB images, and the different modalities on which they are conditioned, can provide additional information for SVBRDF estimation compared to photographs. We compare neural architectures and conditions to identify designs that achieve high accuracy and coherence. We find that, surprisingly, a standard UNet is competitive with more complex designs.en_US
dc.description.sectionheadersAppearance Modelling
dc.description.seriesinformationEurographics Symposium on Rendering
dc.identifier.doi10.2312/sr.20251186
dc.identifier.isbn978-3-03868-292-9
dc.identifier.issn1727-3463
dc.identifier.pages15 pages
dc.identifier.urihttps://doi.org/10.2312/sr.20251186
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/sr20251186
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 -> Texturing; Reflectance modeling
dc.subjectComputing methodologies
dc.subjectTexturing
dc.subjectReflectance modeling
dc.titleAn evaluation of SVBRDF Prediction from Generative Image Models for Appearance Modeling of 3D Scenesen_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
sr20251186.pdf
Size:
21.86 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
gauthieretal_egsr2025_an_evaluation_suppl.pdf
Size:
27.92 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
gauthieretal_egsr2025_cameraready.m4v
Size:
58.54 MB
Format:
Unknown data format
Download
Collections
Rendering 2025 - Symposium Track