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

• URL: http://arxiv.org/abs/2603.03882v1
• Date: Wed, 04 Mar 2026 09:34:16 GMT
• Title: UniSync: Towards Generalizable and High-Fidelity Lip Synchronization for Challenging Scenarios
• Authors: Ruidi Fan, Yang Zhou, Siyuan Wang, Tian Yu, Yutong Jiang, Xusheng Liu,
• Abstract summary: Lip synchronization aims to generate realistic talking videos that match given audio, which is essential for high-quality video dubbing.<n>We propose UniSync, a unified framework designed for achieving high-fidelity lip synchronization in diverse scenarios.<n>We also introduce the RealWorld-LipSync benchmark to evaluate models under real-world demands.
• Score: 20.228570359114105
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• From Inpainting to Editing: A Self-Bootstrapping Framework for Context-Rich Visual Dubbing [24.998261989251976]
  We propose a self-bootstrapping framework that reframes visual dubbing from an ill-posed inpainting task into a well-conditioned video-to-video editing problem.<n>Our approach employs a Diffusion Transformer, first as a data generator, to synthesize ideal training data.<n>A DiDubT-based audio-driven editor is then trained on these pairs end-to-end, leveraging the complete input video frames to focus solely on precise, audio-driven lip modifications.
  arXiv  Detail & Related papers  (2025-12-31T18:58:30Z)
• SyncAnyone: Implicit Disentanglement via Progressive Self-Correction for Lip-Syncing in the wild [16.692450893925148]
  SyncAnyone is a novel two-stage learning framework that achieves accurate motion modeling and high visual fidelity simultaneously.<n>We develop a data generation pipeline that creates pseudo-paired training samples by synthesizing lip-synced videos from the source video.<n>We further tune the stage 2 model on this synthetic data, achieving precise lip editing and better background consistency.
  arXiv  Detail & Related papers  (2025-12-25T16:49:40Z)
• StableDub: Taming Diffusion Prior for Generalized and Efficient Visual Dubbing [63.72095377128904]
  The visual dubbing task aims to generate mouth movements synchronized with the driving audio.<n>Audio-only driving paradigms inadequately capture speaker-specific lip habits.<n>Blind-inpainting approaches produce visual artifacts when handling obstructions.
  arXiv  Detail & Related papers  (2025-09-26T05:23:31Z)
• OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers [18.187498205054748]
  We present OmniSync, a universal lip synchronization framework for diverse visual scenarios.<n>Our approach introduces a mask-free training paradigm using Diffusion Transformer models for direct frame editing without explicit masks.<n>We also establish the AIGCLipSync Benchmark, the first evaluation suite for lip sync in AI-generated videos.
  arXiv  Detail & Related papers  (2025-05-27T17:20:38Z)
• AsynFusion: Towards Asynchronous Latent Consistency Models for Decoupled Whole-Body Audio-Driven Avatars [71.90109867684025]
  Whole-body audio-driven avatar pose and expression generation is a critical task for creating lifelike digital humans.<n>We propose AsynFusion, a novel framework that leverages diffusion transformers to achieve cohesive expression and gesture synthesis.<n>AsynFusion achieves state-of-the-art performance in generating real-time, synchronized whole-body animations.
  arXiv  Detail & Related papers  (2025-05-21T03:28:53Z)
• UniSync: A Unified Framework for Audio-Visual Synchronization [7.120340851879775]
  We present UniSync, a novel approach for evaluating audio-visual synchronization using embedding similarities.<n>We enhance the contrastive learning framework with a margin-based loss component and cross-speaker unsynchronized pairs.<n>UniSync outperforms existing methods on standard datasets.
  arXiv  Detail & Related papers  (2025-03-20T17:16:03Z)
• SimVS: Simulating World Inconsistencies for Robust View Synthesis [102.83898965828621]
  We present an approach for leveraging generative video models to simulate the inconsistencies in the world that can occur during capture.<n>We demonstrate that our world-simulation strategy significantly outperforms traditional augmentation methods in handling real-world scene variations.
  arXiv  Detail & Related papers  (2024-12-10T17:35:12Z)
• ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer [87.32518573172631]
  ReSyncer fuses motion and appearance with unified training. It supports fast personalized fine-tuning, video-driven lip-syncing, the transfer of speaking styles, and even face swapping.
  arXiv  Detail & Related papers  (2024-08-06T16:31:45Z)
• SwapTalk: Audio-Driven Talking Face Generation with One-Shot Customization in Latent Space [13.59798532129008]
  We propose an innovative unified framework, SwapTalk, which accomplishes both face swapping and lip synchronization tasks in the same latent space. We introduce a novel identity consistency metric to more comprehensively assess the identity consistency over time series in generated facial videos. Experimental results on the HDTF demonstrate that our method significantly surpasses existing techniques in video quality, lip synchronization accuracy, face swapping fidelity, and identity consistency.
  arXiv  Detail & Related papers  (2024-05-09T09:22:09Z)
• Audio-driven Talking Face Generation with Stabilized Synchronization Loss [60.01529422759644]
  Talking face generation aims to create realistic videos with accurate lip synchronization and high visual quality. We first tackle the lip leaking problem by introducing a silent-lip generator, which changes the lips of the identity reference to alleviate leakage. Experiments show that our model outperforms state-of-the-art methods in both visual quality and lip synchronization.
  arXiv  Detail & Related papers  (2023-07-18T15:50:04Z)
• StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator [85.40502725367506]
  We propose StyleSync, an effective framework that enables high-fidelity lip synchronization. Specifically, we design a mask-guided spatial information encoding module that preserves the details of the given face. Our design also enables personalized lip-sync by introducing style space and generator refinement on only limited frames.
  arXiv  Detail & Related papers  (2023-05-09T13:38:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.