AnchorSync: Global Consistency Optimization for Long Video Editing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918127825059840 |
|---|---|
| author | Liu, Zichi Wang, Yinggui Wei, Tao Ma, Chao |
| author_facet | Liu, Zichi Wang, Yinggui Wei, Tao Ma, Chao |
| contents | Editing long videos remains a challenging task due to the need for maintaining both global consistency and temporal coherence across thousands of frames. Existing methods often suffer from structural drift or temporal artifacts, particularly in minute-long sequences. We introduce AnchorSync, a novel diffusion-based framework that enables high-quality, long-term video editing by decoupling the task into sparse anchor frame editing and smooth intermediate frame interpolation. Our approach enforces structural consistency through a progressive denoising process and preserves temporal dynamics via multimodal guidance. Extensive experiments show that AnchorSync produces coherent, high-fidelity edits, surpassing prior methods in visual quality and temporal stability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_14609 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AnchorSync: Global Consistency Optimization for Long Video Editing Liu, Zichi Wang, Yinggui Wei, Tao Ma, Chao Computer Vision and Pattern Recognition Editing long videos remains a challenging task due to the need for maintaining both global consistency and temporal coherence across thousands of frames. Existing methods often suffer from structural drift or temporal artifacts, particularly in minute-long sequences. We introduce AnchorSync, a novel diffusion-based framework that enables high-quality, long-term video editing by decoupling the task into sparse anchor frame editing and smooth intermediate frame interpolation. Our approach enforces structural consistency through a progressive denoising process and preserves temporal dynamics via multimodal guidance. Extensive experiments show that AnchorSync produces coherent, high-fidelity edits, surpassing prior methods in visual quality and temporal stability. |
| title | AnchorSync: Global Consistency Optimization for Long Video Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.14609 |