UniSync: Towards Generalizable and High-Fidelity Lip Synchronization for Challenging Scenarios

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fan, Ruidi, Zhou, Yang, Wang, Siyuan, Yu, Tian, Jiang, Yutong, Liu, Xusheng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910040414224384
author Fan, Ruidi
Zhou, Yang
Wang, Siyuan
Yu, Tian
Jiang, Yutong
Liu, Xusheng
author_facet Fan, Ruidi
Zhou, Yang
Wang, Siyuan
Yu, Tian
Jiang, Yutong
Liu, Xusheng
contents Lip synchronization aims to generate realistic talking videos that match given audio, which is essential for high-quality video dubbing. However, current methods have fundamental drawbacks: mask-based approaches suffer from local color discrepancies, while mask-free methods struggle with global background texture misalignment. Furthermore, most methods struggle with diverse real-world scenarios such as stylized avatars, face occlusion, and extreme lighting conditions. In this paper, we propose UniSync, a unified framework designed for achieving high-fidelity lip synchronization in diverse scenarios. Specifically, UniSync uses a mask-free pose-anchored training strategy to keep head motion and eliminate synthesis color artifacts, while employing mask-based blending consistent inference to ensure structural precision and smooth blending. Notably, fine-tuning on compact but diverse videos empowers our model with exceptional domain adaptability, handling complex corner cases effectively. We also introduce the RealWorld-LipSync benchmark to evaluate models under real-world demands, which covers diverse application scenarios including both human faces and stylized avatars. Extensive experiments demonstrate that UniSync significantly outperforms state-of-the-art methods, advancing the field towards truly generalizable and production-ready lip synchronization.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03882
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UniSync: Towards Generalizable and High-Fidelity Lip Synchronization for Challenging Scenarios
Fan, Ruidi
Zhou, Yang
Wang, Siyuan
Yu, Tian
Jiang, Yutong
Liu, Xusheng
Computer Vision and Pattern Recognition
Lip synchronization aims to generate realistic talking videos that match given audio, which is essential for high-quality video dubbing. However, current methods have fundamental drawbacks: mask-based approaches suffer from local color discrepancies, while mask-free methods struggle with global background texture misalignment. Furthermore, most methods struggle with diverse real-world scenarios such as stylized avatars, face occlusion, and extreme lighting conditions. In this paper, we propose UniSync, a unified framework designed for achieving high-fidelity lip synchronization in diverse scenarios. Specifically, UniSync uses a mask-free pose-anchored training strategy to keep head motion and eliminate synthesis color artifacts, while employing mask-based blending consistent inference to ensure structural precision and smooth blending. Notably, fine-tuning on compact but diverse videos empowers our model with exceptional domain adaptability, handling complex corner cases effectively. We also introduce the RealWorld-LipSync benchmark to evaluate models under real-world demands, which covers diverse application scenarios including both human faces and stylized avatars. Extensive experiments demonstrate that UniSync significantly outperforms state-of-the-art methods, advancing the field towards truly generalizable and production-ready lip synchronization.
title UniSync: Towards Generalizable and High-Fidelity Lip Synchronization for Challenging Scenarios
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.03882