3D Gaussian Blendshapes for Head Avatar Animation

Shengjie Ma, Yanlin Weng, Tianjia Shao, Kun Zhou
4/30/2024
cs.GRcs.CV

No official code found. Best implementation: zjumsj/GaussianBlendshapes (200 stars, GPL-3.0, last commit 2025-06-29).

Abstract

We introduce 3D Gaussian blendshapes for modeling photorealistic head avatars. Taking a monocular video as input, we learn a base head model of neutral expression, along with a group of expression blendshapes, each of which corresponds to a basis expression in classical parametric face models. Both the neutral model and expression blendshapes are represented as 3D Gaussians, which contain a few properties to depict the avatar appearance. The avatar model of an arbitrary expression can be effectively generated by combining the neutral model and expression blendshapes through linear blending of Gaussians with the expression coefficients. High-fidelity head avatar animations can be synthesized in real time using Gaussian splatting. Compared to state-of-the-art methods, our Gaussian blendshape representation better captures high-frequency details exhibited in input video, and achieves superior rendering performance.

View on arXivView PDF

Code Implementations(1)

zjumsj/GaussianBlendshapesCommunity71%
GPL-3.0

Official PyTorch implementation of the paper "3D Gaussian Blendshapes for Head Avatar Animation"

20021C, C++Aug 3, 20241 years agoGPL-3.0

Similar Papers

GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstruction

89% match1 repo232024

GANHead: Towards Generative Animatable Neural Head Avatars

88% match1 repo792026

TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modeling

88% match2025

Gaussian Eigen Models for Human Heads

88% match1 repo542026

HRAvatar: High-Quality and Relightable Gaussian Head Avatar

88% match2 repos1122026

HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior

87% match1 repo1602024

Cite this paper

@article{ma2024gaussian,
  title  = {3D Gaussian Blendshapes for Head Avatar Animation},
  author = {Shengjie Ma and Yanlin Weng and Tianjia Shao and Kun Zhou},
  year   = {2024},
  eprint = {2404.19398},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.19398v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.19398.svg)](https://codeofpaper.com/paper/2404.19398)

Discussion