HRAvatar: High-Quality and Relightable Gaussian Head Avatar

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Dongbin, Liu, Yunfei, Lin, Lijian, Zhu, Ye, Chen, Kangjie, Qin, Minghan, Li, Yu, Wang, Haoqian
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866916697917620224
author	Zhang, Dongbin Liu, Yunfei Lin, Lijian Zhu, Ye Chen, Kangjie Qin, Minghan Li, Yu Wang, Haoqian
author_facet	Zhang, Dongbin Liu, Yunfei Lin, Lijian Zhu, Ye Chen, Kangjie Qin, Minghan Li, Yu Wang, Haoqian
contents	Reconstructing animatable and high-quality 3D head avatars from monocular videos, especially with realistic relighting, is a valuable task. However, the limited information from single-view input, combined with the complex head poses and facial movements, makes this challenging. Previous methods achieve real-time performance by combining 3D Gaussian Splatting with a parametric head model, but the resulting head quality suffers from inaccurate face tracking and limited expressiveness of the deformation model. These methods also fail to produce realistic effects under novel lighting conditions. To address these issues, we propose HRAvatar, a 3DGS-based method that reconstructs high-fidelity, relightable 3D head avatars. HRAvatar reduces tracking errors through end-to-end optimization and better captures individual facial deformations using learnable blendshapes and learnable linear blend skinning. Additionally, it decomposes head appearance into several physical properties and incorporates physically-based shading to account for environmental lighting. Extensive experiments demonstrate that HRAvatar not only reconstructs superior-quality heads but also achieves realistic visual effects under varying lighting conditions.
format	Preprint
id	arxiv_https___arxiv_org_abs_2503_08224
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	HRAvatar: High-Quality and Relightable Gaussian Head Avatar Zhang, Dongbin Liu, Yunfei Lin, Lijian Zhu, Ye Chen, Kangjie Qin, Minghan Li, Yu Wang, Haoqian Computer Vision and Pattern Recognition Reconstructing animatable and high-quality 3D head avatars from monocular videos, especially with realistic relighting, is a valuable task. However, the limited information from single-view input, combined with the complex head poses and facial movements, makes this challenging. Previous methods achieve real-time performance by combining 3D Gaussian Splatting with a parametric head model, but the resulting head quality suffers from inaccurate face tracking and limited expressiveness of the deformation model. These methods also fail to produce realistic effects under novel lighting conditions. To address these issues, we propose HRAvatar, a 3DGS-based method that reconstructs high-fidelity, relightable 3D head avatars. HRAvatar reduces tracking errors through end-to-end optimization and better captures individual facial deformations using learnable blendshapes and learnable linear blend skinning. Additionally, it decomposes head appearance into several physical properties and incorporates physically-based shading to account for environmental lighting. Extensive experiments demonstrate that HRAvatar not only reconstructs superior-quality heads but also achieves realistic visual effects under varying lighting conditions.
title	HRAvatar: High-Quality and Relightable Gaussian Head Avatar
topic	Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2503.08224