Personalized 3D Talking Head Animation with Style Preservation

Published:Dec 27, 2025 14:14
1 min read
ArXiv

Analysis

This paper addresses the limitations of existing speech-driven 3D talking head generation methods by focusing on personalization and realism. It introduces a novel framework, PTalker, that disentangles speaking style from audio and facial motion, and enhances lip-synchronization accuracy. The key contribution is the ability to generate realistic, identity-specific speaking styles, which is a significant advancement in the field.

Reference

PTalker effectively generates realistic, stylized 3D talking heads that accurately match identity-specific speaking styles, outperforming state-of-the-art methods.