Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation

arXiv:2606.31088v1 Announce Type: new Abstract: Conversational talking face generation has recently attracted increasing attention, aiming to synthesize interactive talking videos where characters speak, listen, and respond dynamically to each other. This task presents three core challenges: 1) Flexibility: enabling multi-round dialogues with an arbitrary number of participants; 2) Naturalness: maintaining coherent motion and appropriate non-verbal feedback throughout the interaction; and 3) Eff...

arXiv cs.CV ·Baiqin Wang, Sen Chen, Jiankuo Zhao, Xiangyu Liu, Zhen Lei, Xiangyu Zhu ·
compartilhar: