GGAvatar: Dynamic Facial Geometric Adjustment for Gaussian Head Avatar

Simple item page
dc.contributor.authorLi, Xinyangen_US
dc.contributor.authorWang, Jiaxinen_US
dc.contributor.authorXuan, Yixinen_US
dc.contributor.authorYao, Gongxinen_US
dc.contributor.authorPan, Yuen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:05:18Z
dc.date.available2024-10-13T18:05:18Z
dc.date.issued2024
dc.description.abstractReconstructing animatable 3D head avatars from target subject videos has long been a significant challenge and a hot topic in computer graphics. This paper proposes GGAvatar, a novel 3D avatar representation designed to robustly model dynamic head avatars with complex identities and deformations. GGAvatar employs a coarse-to-fine structure, featuring two core modules: a Neutral Gaussian Initialization Module and a Geometry Morph Adjuster. The Neutral Gaussian Initialization Module pairs Gaussian primitives with deformable triangular meshes, using an adaptive density control strategy to model the geometric structure of the target subject with neutral expressions. The Geometry Morph Adjuster introduces deformation bases for each Gaussian in global space, creating fine-grained low-dimensional representations of deformations to overcome the limitations of the Linear Blend Skinning formula. Extensive experiments show that GGAvatar can produce high-fidelity renderings, outperforming state-of-the-art methods in visual quality and quantitative metrics.en_US
dc.description.sectionheadersHuman I
dc.description.seriesinformationPacific Graphics Conference Papers and Posters
dc.identifier.doi10.2312/pg.20241313
dc.identifier.isbn978-3-03868-250-9
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20241313
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20241313
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 → Reconstruction; Animation; Shape modeling
dc.subjectComputing methodologies → Reconstruction
dc.subjectAnimation
dc.subjectShape modeling
dc.titleGGAvatar: Dynamic Facial Geometric Adjustment for Gaussian Head Avataren_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
pg20241313.pdf
Size:
2.48 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
demo.mp4
Size:
8.26 MB
Format:
Video MP4
Download
Thumbnail Image
Name:
supplementary_material.pdf
Size:
5.37 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2024 Conference Papers and Posters