# VividTalk

## VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior

[Xusen Sun](https://dblp.org/pid/308/0824) , [Longhao Zhang](https://scholar.google.com/citations?user=qkJD6c0AAAAJ\&hl=zh-CN) , [Hao Zhu](http://zhuhao.cc/home/) , [Peng Zhang](https://scholar.google.com/citations?user=QTgxKmkAAAAJ\&hl=zh-CN) , [Bang Zhang](https://dblp.org/pid/11/4046.html) , [Xinya Ji](https://dblp.org/pid/290/1747) , [Kangneng Zhou](https://scholar.google.com.hk/citations?user=y1vvxWYAAAAJ\&hl=zh-CN)  [Daiheng Gao](https://tomguluson92.github.io/) , [Liefeng Bo](https://scholar.google.com/citations?user=FJwtMf0AAAAJ\&hl=zh-CN) , [Xun Cao](https://scholar.google.com/citations?user=8hZIngIAAAAJ\&hl=zh-CN\&oi=ao) Nanjing University,  Alibaba Group,  ByteDance,  Nankai University.

{% embed url="<https://humanaigc.github.io/vivid-talk/>" %}
<https://humanaigc.github.io/vivid-talk/>   &#x20;
{% endembed %}

{% embed url="<https://github.com/HumanAIGC/VividTalk>" %}
<https://github.com/HumanAIGC/VividTalk>   &#x20;
{% endembed %}

{% embed url="<https://www.youtube.com/watch?v=lJVzt7JCe_4>" %}
<https://www.youtube.com/watch?v=lJVzt7JCe_4>      &#x20;
{% endembed %}