Implicit Neural Deformation for Sparse-View Face Reconstruction

Simple item page
dc.contributor.authorLi, Moranen_US
dc.contributor.authorHuang, Haibinen_US
dc.contributor.authorZheng, Yien_US
dc.contributor.authorLi, Mengtianen_US
dc.contributor.authorSang, Nongen_US
dc.contributor.authorMa, Chongyangen_US
dc.contributor.editorUmetani, Nobuyukien_US
dc.contributor.editorWojtan, Chrisen_US
dc.contributor.editorVouga, Etienneen_US
dc.date.accessioned2022-10-04T06:41:56Z
dc.date.available2022-10-04T06:41:56Z
dc.date.issued2022
dc.description.abstractIn this work, we present a new method for 3D face reconstruction from sparse-view RGB images. Unlike previous methods which are built upon 3D morphable models (3DMMs) with limited details, we leverage an implicit representation to encode rich geometric features. Our overall pipeline consists of two major components, including a geometry network, which learns a deformable neural signed distance function (SDF) as the 3D face representation, and a rendering network, which learns to render on-surface points of the neural SDF to match the input images via self-supervised optimization. To handle in-the-wild sparse-view input of the same target with different expressions at test time, we propose residual latent code to effectively expand the shape space of the learned implicit face representation as well as a novel view-switch loss to enforce consistency among different views. Our experimental results on several benchmark datasets demonstrate that our approach outperforms alternative baselines and achieves superior face reconstruction results compared to state-of-the-art methods.en_US
dc.description.number7
dc.description.sectionheadersDigital Human
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14704
dc.identifier.issn1467-8659
dc.identifier.pages601-610
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14704
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14704
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Mesh models; Shape analysis
dc.subjectComputing methodologies → Mesh models
dc.subjectShape analysis
dc.titleImplicit Neural Deformation for Sparse-View Face Reconstructionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v41i7pp601-610.pdf
Size:
25.93 MB
Format:
Adobe Portable Document Format
Download
Collections
41-Issue 7