/HeadStudio

[ECCV 2024] HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting.

Primary LanguagePythonMIT LicenseMIT

HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting

Zhenglin Zhou · Fan Ma · Hehe Fan · Yi Yang*

ReLER, CCAI, Zhejiang University

*corresponding authors

GitHub

demo_arxiv.mp4

Text to Head Avatars Generation

Text-based animatable avatars generation by HeadStudio.

Comparison with Previous Works

Comparison with the text to static avatar generation methods. HeadStudio excels at producing high-fidelity head avatars, yielding superior results.

Comparison with the text to dynamic avatar generation methods. HeadStudio provides effective semantic alignment, smooth expression deformation, and real-time rendering.

Acknowledgements

  • HeadStudio is developed by ReLER at Zhejiang University, all copyright reserved.
  • Thanks threestudio, we use it as base framework.
  • Thanks PlayHT, we use it for text to audio generation.
  • Thanks TalkSHOW, we use it for audio-based avatar driven.

Cite

If you find HeadStudio useful for your research and applications, please cite us using this BibTeX:

@article{zhou2024headstudio,
  author = {Zhenglin Zhou and Fan Ma and Hehe Fan and Yi Yang},
  title = {HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting},
  journal={arXiv preprint arXiv:2402.06149},
  year={2024}
}