HighSync: High-Quality Lip Synchronization via Latent Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914572315656192 |
|---|---|
| author | Daghigh, Saeed Firouzi Mobarekeh, Majid Iranpour Alavi, Mostafa Bagheri, Mehdi |
| author_facet | Daghigh, Saeed Firouzi Mobarekeh, Majid Iranpour Alavi, Mostafa Bagheri, Mehdi |
| contents | We present HighSync, an end-to-end diffusion-based framework for high-fidelity lip synchronization that generates photorealistic talking-face videos aligned with arbitrary input audio. Existing approaches consistently struggle to reconcile image quality with synchronization accuracy, producing either visually degraded outputs or temporally inconsistent lip movements. HighSync addresses both challenges simultaneously and, to our knowledge, is the first lip sync model to operate natively at 512*512 resolution, positioning it as a viable solution for professional production environments such as the film and broadcast industries. Central to our approach is the identification and systematic elimination of a data leakage phenomenon that has silently undermined temporal modeling in prior work, preventing models from developing a genuine dependence on the audio signal. Comprehensive evaluations across both perceptual quality and synchronization accuracy metrics confirm that HighSync achieves state-of-the-art performance on both fronts. Source code, pre-trained models, and supplementary video results are publicly available at: https://github.com/saeed5959/high_sync |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_16918 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HighSync: High-Quality Lip Synchronization via Latent Diffusion Models Daghigh, Saeed Firouzi Mobarekeh, Majid Iranpour Alavi, Mostafa Bagheri, Mehdi Computer Vision and Pattern Recognition We present HighSync, an end-to-end diffusion-based framework for high-fidelity lip synchronization that generates photorealistic talking-face videos aligned with arbitrary input audio. Existing approaches consistently struggle to reconcile image quality with synchronization accuracy, producing either visually degraded outputs or temporally inconsistent lip movements. HighSync addresses both challenges simultaneously and, to our knowledge, is the first lip sync model to operate natively at 512*512 resolution, positioning it as a viable solution for professional production environments such as the film and broadcast industries. Central to our approach is the identification and systematic elimination of a data leakage phenomenon that has silently undermined temporal modeling in prior work, preventing models from developing a genuine dependence on the audio signal. Comprehensive evaluations across both perceptual quality and synchronization accuracy metrics confirm that HighSync achieves state-of-the-art performance on both fronts. Source code, pre-trained models, and supplementary video results are publicly available at: https://github.com/saeed5959/high_sync |
| title | HighSync: High-Quality Lip Synchronization via Latent Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.16918 |