EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MGAvatar: Mesh‐Bound Gaussians for Head Avatar Geometry and Appearance Modeling

Lei Shi, Sen Peng, Zhiyang Deng, Zhonggui Chen, Xiaohu Guo, Baorong Yang, Xiao Dong

Computer Graphics Forum · 14.11.2026

DOI: 10.1111/cgf.70630 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 14.11.2026. Verfasst von Lei Shi und 6 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate head modeling requires a stable yet expressive geometric representation. Existing Gaussian‐based head avatars commonly rely on parametric templates (e.g., FLAME) for Gaussian initialization and deformation, but these templates lack personalized priors and struggle to represent structures such as hair and clothing. To address this issue, we propose MGAvatar, a Gaussian–mesh hybrid representation that jointly models geometry and appearance through two Gaussian–mesh binding modes. Specifically, we introduce vertex‐bound Gaussians and constrain their learnable parameters, enabling progressive mesh deformation to represent complex head geometry, while a pose‐dependent offset module accounts for non‐rigid deformations. Once geometry is stabilized, MGAvatar switches to face‐bound Gaussians for appearance modeling. To improve appearance consistency across novel poses and viewpoints, we introduce a view‐conditioned neural color field that alleviates artifacts caused by independently optimized Gaussian colors. In addition, we design a Gaussian offset network to predict Gaussian offset maps in the observation space, providing greater flexibility for face‐bound Gaussians to capture dynamic facial textures. Extensive experiments on multi‐view and monocular videos show that MGAvatar outperforms existing methods in rendering quality, producing high‐fidelity head avatars with rich texture details.

Zitieren

APA

Shi, L., Peng, S., Deng, Z., Chen, Z., Guo, X., Yang, B., & Dong, X. (2026). MGAvatar: Mesh‐Bound Gaussians for Head Avatar Geometry and Appearance Modeling. Computer Graphics Forum. https://doi.org/10.1111/cgf.70630

Vancouver

Shi L, Peng S, Deng Z, Chen Z, Guo X, Yang B, et al. MGAvatar: Mesh‐Bound Gaussians for Head Avatar Geometry and Appearance Modeling. Computer Graphics Forum. 2026. doi:10.1111/cgf.70630

BibTeX
@article{Shi2026,
  author = {Shi, Lei and Peng, Sen and Deng, Zhiyang and Chen, Zhonggui and Guo, Xiaohu and Yang, Baorong and Dong, Xiao},
  title = {MGAvatar: Mesh‐Bound Gaussians for Head Avatar Geometry and Appearance Modeling},
  journal = {Computer Graphics Forum},
  year = {2026},
  doi = {10.1111/cgf.70630}
}
Kostenlos starten →