Joint Gaussian Deformation in Triangle-Deformed Space for High-Fidelity Head Avatars

Simple item page
dc.contributor.authorLu, Jiaweien_US
dc.contributor.authorGuang, Kunxinen_US
dc.contributor.authorHao, Conghuien_US
dc.contributor.authorSun, Kaien_US
dc.contributor.authorYang, Jianen_US
dc.contributor.authorXie, Jinen_US
dc.contributor.authorWang, Beibeien_US
dc.contributor.editorWang, Beibeien_US
dc.contributor.editorWilkie, Alexanderen_US
dc.date.accessioned2025-06-20T07:49:36Z
dc.date.available2025-06-20T07:49:36Z
dc.date.issued2025
dc.description.abstractCreating 3D human heads with mesoscale details and high-fidelity animation from monocular or sparse multi-view videos is challenging. While 3D Gaussian splatting (3DGS) has brought significant benefits into this task, due to its powerful representation ability and rendering speed, existing works still face several issues, including inaccurate and blurry deformation, and lack of detailed appearance, due to difficulties in complex deformation representation and unreasonable Gaussian placement. In this paper, we propose a joint Gaussian deformation method by decoupling the complex deformation into two simpler deformations, incorporating a learnable displacement map-guided Gaussian-triangle binding and a neural-based deformation refinement, improving the fidelity of animation and details of reconstructed head avatars. However, renderings of reconstructed head avatars at unseen views still show artifacts, due to overfitting on sparse input views. To address this issue, we leverage synthesized pseudo views rendered with fitted textured 3DMMs as priors to initialize Gaussians, which helps maintain a consistent and realistic appearance across various views. As a result, our method outperforms existing state-of-the-art approaches with about 4.3 dB PSNR in novel-view synthesis and about 0.9 dB PSNR in self-reenactment on multi-view video datasets. Our method also preserves high-frequency details, exhibits more accurate deformations, and significantly reduces artifacts in unseen views.en_US
dc.description.sectionheadersGaussians
dc.description.seriesinformationEurographics Symposium on Rendering
dc.identifier.doi10.2312/sr.20251189
dc.identifier.isbn978-3-03868-292-9
dc.identifier.issn1727-3463
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.2312/sr.20251189
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/sr20251189
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
dc.subjectComputing methodologies
dc.subjectRendering
dc.titleJoint Gaussian Deformation in Triangle-Deformed Space for High-Fidelity Head Avatarsen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
sr20251189.pdf
Size:
27.5 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1008_mm1.mp4
Size:
52.7 MB
Format:
Video MP4
Download
Collections
Rendering 2025 - Symposium Track