EARTalking: End-to-end GPT-style Autoregressive Talking Head Synthesis with Frame-wise Control

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Weng, Yuzhe, Wang, Haotian, Yu, Yuanhong, Du, Jun, He, Shan, Wu, Xiaoyan, Xu, Haoran
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Multimedia Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.20307