GGAvatar: Geometric Adjustment of Gaussian Head Avatar

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Xinyang, Wang, Jiaxin, Xuan, Yixin, Yao, Gongxin, Pan, Yu
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913357012926464
author Li, Xinyang
Wang, Jiaxin
Xuan, Yixin
Yao, Gongxin
Pan, Yu
author_facet Li, Xinyang
Wang, Jiaxin
Xuan, Yixin
Yao, Gongxin
Pan, Yu
contents We propose 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: Neutral Gaussian Initialization Module and Geometry Morph Adjuster. Neutral Gaussian Initialization Module pairs Gaussian primitives with deformable triangular meshes, employing an adaptive density control strategy to model the geometric structure of the target subject with neutral expressions. Geometry Morph Adjuster introduces deformation bases for each Gaussian in global space, creating fine-grained low-dimensional representations of deformation behaviors to address the Linear Blend Skinning formula's limitations effectively. Extensive experiments show that GGAvatar can produce high-fidelity renderings, outperforming state-of-the-art methods in visual quality and quantitative metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11993
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GGAvatar: Geometric Adjustment of Gaussian Head Avatar
Li, Xinyang
Wang, Jiaxin
Xuan, Yixin
Yao, Gongxin
Pan, Yu
Computer Vision and Pattern Recognition
We propose 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: Neutral Gaussian Initialization Module and Geometry Morph Adjuster. Neutral Gaussian Initialization Module pairs Gaussian primitives with deformable triangular meshes, employing an adaptive density control strategy to model the geometric structure of the target subject with neutral expressions. Geometry Morph Adjuster introduces deformation bases for each Gaussian in global space, creating fine-grained low-dimensional representations of deformation behaviors to address the Linear Blend Skinning formula's limitations effectively. Extensive experiments show that GGAvatar can produce high-fidelity renderings, outperforming state-of-the-art methods in visual quality and quantitative metrics.
title GGAvatar: Geometric Adjustment of Gaussian Head Avatar
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.11993