Monocular and Generalizable Gaussian Talking Head Animation

Shengjie Gong; Haojie Li; Jiapeng Tang; Dongming Hu; Shuangping Huang; Hao Chen; Tianshui Chen; Zhuoman Liu

doi:10.1109/cvpr52734.2025.00519

CVPR2025顶会

Monocular and Generalizable Gaussian Talking Head Animation

Shengjie Gong, Haojie Li, Jiapeng Tang, Dongming Hu, Shuangping Huang, Hao Chen, Tianshui Chen, Zhuoman Liu

DOI 出版方

2025年份

8顶会引用

摘要

Real-Time Inference on Unseen Identities (>40FPS) Driving Video Single Reference Monucular Training Monucular Dataset "two hundred thousand" Figure 1. MGGTalk is trained using only monocular datasets and enable generalizing to unseen identities without personalized re-training. Additionally, it supports real-time generation of talking heads in diverse poses and novel viewpoints.