Two-shot Shape and SVBRDF Reconstruction of Human Faces with Albedo-Conditioned Diffusion

Simple item page
dc.contributor.authorFan, Chongruien_US
dc.contributor.authorLin, Yimingen_US
dc.contributor.authorLin, Arvinen_US
dc.contributor.authorGhosh, Abhijeeten_US
dc.contributor.editorCeylan, Duyguen_US
dc.contributor.editorLi, Tzu-Maoen_US
dc.date.accessioned2025-05-09T09:35:38Z
dc.date.available2025-05-09T09:35:38Z
dc.date.issued2025
dc.description.abstractReconstructing 3D human heads with relightability has been a long-standing research problem. Most methods either require a complicated hardware setup for multiview capture or involve fitting a pre-learned morphable model, resulting in a loss of details. In our work, we present a two-step deep learning method that directly predicts the shape and SVBRDF of a subject's face given two images taken from each side of the face. We enhance SVBRDF prediction by first estimating the diffuse and specular albedo in image space, then generating texture maps in UV-space with a generative model. We also learn a 2D position map in UVspace for 3D geometry, eliminating the need for a morphable model. Contrary to single-image facial reconstruction methods, we obtain clear measurements on both sides of the face with two images. Our method outperforms state-of-the-art methods when rendering faces at extreme angles and provides texture maps that are directly usable in most rendering systems.en_US
dc.description.sectionheadersShort Paper 2
dc.description.seriesinformationEurographics 2025 - Short Papers
dc.identifier.doi10.2312/egs.20251038
dc.identifier.isbn978-3-03868-268-4
dc.identifier.issn1017-4656
dc.identifier.pages4 pages
dc.identifier.urihttps://doi.org/10.2312/egs.20251038
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/egs20251038
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 → Reflectance modeling; Shape modeling
dc.subjectComputing methodologies → Reflectance modeling
dc.subjectShape modeling
dc.titleTwo-shot Shape and SVBRDF Reconstruction of Human Faces with Albedo-Conditioned Diffusionen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
egs20251038.pdf
Size:
47.78 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
short1012_supp.pdf
Size:
36.74 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2025 - Short Papers