NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912939702747136 |
|---|---|
| author | Pan, Tianlin Dai, Jiayi Yuan, Chenpu Lv, Zhengyao Yang, Binxin Yin, Hubery Li, Chen Lyu, Jing Shan, Caifeng Si, Chenyang |
| author_facet | Pan, Tianlin Dai, Jiayi Yuan, Chenpu Lv, Zhengyao Yang, Binxin Yin, Hubery Li, Chen Lyu, Jing Shan, Caifeng Si, Chenyang |
| contents | Recent video editing models have achieved impressive results, but most still require large-scale paired datasets. Collecting such naturally aligned pairs at scale remains highly challenging and constitutes a critical bottleneck, especially for local video editing data. Existing workarounds transfer image editing to video through global motion control for pair-free video editing, but such designs struggle with background and temporal consistency. In this paper, we propose NOVA: Sparse Control \& Dense Synthesis, a new framework for unpaired video editing. Specifically, the sparse branch provides semantic guidance through user-edited keyframes distributed across the video, and the dense branch continuously incorporates motion and texture information from the original video to maintain high fidelity and coherence. Moreover, we introduce a degradation-simulation training strategy that enables the model to learn motion reconstruction and temporal consistency by training on artificially degraded videos, thus eliminating the need for paired data. Our extensive experiments demonstrate that NOVA outperforms existing approaches in edit fidelity, motion preservation, and temporal coherence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02802 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing Pan, Tianlin Dai, Jiayi Yuan, Chenpu Lv, Zhengyao Yang, Binxin Yin, Hubery Li, Chen Lyu, Jing Shan, Caifeng Si, Chenyang Computer Vision and Pattern Recognition Recent video editing models have achieved impressive results, but most still require large-scale paired datasets. Collecting such naturally aligned pairs at scale remains highly challenging and constitutes a critical bottleneck, especially for local video editing data. Existing workarounds transfer image editing to video through global motion control for pair-free video editing, but such designs struggle with background and temporal consistency. In this paper, we propose NOVA: Sparse Control \& Dense Synthesis, a new framework for unpaired video editing. Specifically, the sparse branch provides semantic guidance through user-edited keyframes distributed across the video, and the dense branch continuously incorporates motion and texture information from the original video to maintain high fidelity and coherence. Moreover, we introduce a degradation-simulation training strategy that enables the model to learn motion reconstruction and temporal consistency by training on artificially degraded videos, thus eliminating the need for paired data. Our extensive experiments demonstrate that NOVA outperforms existing approaches in edit fidelity, motion preservation, and temporal coherence. |
| title | NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.02802 |