SyncAnyone: Implicit Disentanglement via Progressive Self-Correction for Lip-Syncing in the wild

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xindi, Meng, Dechao, Xiao, Steven, Wang, Qi, Zhang, Peng, Zhang, Bang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914310117130240
author Zhang, Xindi
Meng, Dechao
Xiao, Steven
Wang, Qi
Zhang, Peng
Zhang, Bang
author_facet Zhang, Xindi
Meng, Dechao
Xiao, Steven
Wang, Qi
Zhang, Peng
Zhang, Bang
contents High-quality AI-powered video dubbing demands precise audio-lip synchronization, high-fidelity visual generation, and faithful preservation of identity and background. Most existing methods rely on a mask-based training strategy, where the mouth region is masked in talking-head videos, and the model learns to synthesize lip movements from corrupted inputs and target audios. While this facilitates lip-sync accuracy, it disrupts spatiotemporal context, impairing performance on dynamic facial motions and causing instability in facial structure and background consistency. To overcome this limitation, we propose SyncAnyone, a novel two-stage learning framework that achieves accurate motion modeling and high visual fidelity simultaneously. In Stage 1, we train a diffusion-based video transformer for masked mouth inpainting, leveraging its strong spatiotemporal modeling to generate accurate, audio-driven lip movements. However, due to input corruption, minor artifacts may arise in the surrounding facial regions and the background. In Stage 2, we develop a mask-free tuning pipeline to address mask-induced artifacts. Specifically, on the basis of the Stage 1 model, we develop a data generation pipeline that creates pseudo-paired training samples by synthesizing lip-synced videos from the source video and random sampled audio. We further tune the stage 2 model on this synthetic data, achieving precise lip editing and better background consistency. Extensive experiments show that our method achieves state-of-the-art results in visual quality, temporal coherence, and identity preservation under in-the wild lip-syncing scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21736
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SyncAnyone: Implicit Disentanglement via Progressive Self-Correction for Lip-Syncing in the wild
Zhang, Xindi
Meng, Dechao
Xiao, Steven
Wang, Qi
Zhang, Peng
Zhang, Bang
Computer Vision and Pattern Recognition
High-quality AI-powered video dubbing demands precise audio-lip synchronization, high-fidelity visual generation, and faithful preservation of identity and background. Most existing methods rely on a mask-based training strategy, where the mouth region is masked in talking-head videos, and the model learns to synthesize lip movements from corrupted inputs and target audios. While this facilitates lip-sync accuracy, it disrupts spatiotemporal context, impairing performance on dynamic facial motions and causing instability in facial structure and background consistency. To overcome this limitation, we propose SyncAnyone, a novel two-stage learning framework that achieves accurate motion modeling and high visual fidelity simultaneously. In Stage 1, we train a diffusion-based video transformer for masked mouth inpainting, leveraging its strong spatiotemporal modeling to generate accurate, audio-driven lip movements. However, due to input corruption, minor artifacts may arise in the surrounding facial regions and the background. In Stage 2, we develop a mask-free tuning pipeline to address mask-induced artifacts. Specifically, on the basis of the Stage 1 model, we develop a data generation pipeline that creates pseudo-paired training samples by synthesizing lip-synced videos from the source video and random sampled audio. We further tune the stage 2 model on this synthetic data, achieving precise lip editing and better background consistency. Extensive experiments show that our method achieves state-of-the-art results in visual quality, temporal coherence, and identity preservation under in-the wild lip-syncing scenarios.
title SyncAnyone: Implicit Disentanglement via Progressive Self-Correction for Lip-Syncing in the wild
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.21736