首页|期刊导航|计算可视媒体（英文）|Decoupled two-stage talking head generation via Gaussian-landmark-based neural radiance fields

Decoupled two-stage talking head generation via Gaussian-landmark-based neural radiance fields

Boyao Ma Yuanping Cao Lei Zhang

计算可视媒体（英文）2025，Vol.11Issue(4)：799-816,18.

计算可视媒体（英文）2025，Vol.11Issue(4)：799-816,18.DOI:10.26599/CVM.2025.9450482

Decoupled two-stage talking head generation via Gaussian-landmark-based neural radiance fields

Boyao Ma ¹Yuanping Cao ¹Lei Zhang¹

作者信息

1. School of Computer,Beijing Institute of Technology,Beijing 100081,China
折叠

摘要

关键词

audio-driven generation/talking head/Transformer/neural radiance fields(NeRF)rendering

Key words

audio-driven generation/talking head/Transformer/neural radiance fields(NeRF)rendering

引用本文复制引用

Boyao Ma,Yuanping Cao,Lei Zhang..Decoupled two-stage talking head generation via Gaussian-landmark-based neural radiance fields[J].计算可视媒体（英文）,2025,11(4):799-816,18.

基金项目

The authors would like to thank the anonymous reviewers for their helpful comments.This work was supported in part by the Natural Science Foundation of Shandong Province(ZR2024ZD12). （ZR2024ZD12）

计算可视媒体（英文）

访问量0

下载量0

段落导航