Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.16920 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918255516450816 |
|---|---|
| author | Mai, Jinjie Wang, Chaoyang Qian, Guocheng Gordon Menapace, Willi Tulyakov, Sergey Ghanem, Bernard Wonka, Peter Mirzaei, Ashkan |
| author_facet | Mai, Jinjie Wang, Chaoyang Qian, Guocheng Gordon Menapace, Willi Tulyakov, Sergey Ghanem, Bernard Wonka, Peter Mirzaei, Ashkan |
| contents | While image editing has advanced rapidly, video editing remains less explored, facing challenges in consistency, control, and generalization. We study the design space of data, architecture, and control, and introduce \emph{EasyV2V}, a simple and effective framework for instruction-based video editing. On the data side, we compose existing experts with fast inverses to build diverse video pairs, lift image edit pairs into videos via single-frame supervision and pseudo pairs with shared affine motion, mine dense-captioned clips for video pairs, and add transition supervision to teach how edits unfold. On the model side, we observe that pretrained text-to-video models possess editing capability, motivating a simplified design. Simple sequence concatenation for conditioning with light LoRA fine-tuning suffices to train a strong model. For control, we unify spatiotemporal control via a single mask mechanism and support optional reference images. Overall, EasyV2V works with flexible inputs, e.g., video+text, video+mask+text, video+mask+reference+text, and achieves state-of-the-art video editing results, surpassing concurrent and commercial systems. Project page: https://snap-research.github.io/easyv2v/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_16920 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EasyV2V: A High-quality Instruction-based Video Editing Framework Mai, Jinjie Wang, Chaoyang Qian, Guocheng Gordon Menapace, Willi Tulyakov, Sergey Ghanem, Bernard Wonka, Peter Mirzaei, Ashkan Computer Vision and Pattern Recognition Artificial Intelligence While image editing has advanced rapidly, video editing remains less explored, facing challenges in consistency, control, and generalization. We study the design space of data, architecture, and control, and introduce \emph{EasyV2V}, a simple and effective framework for instruction-based video editing. On the data side, we compose existing experts with fast inverses to build diverse video pairs, lift image edit pairs into videos via single-frame supervision and pseudo pairs with shared affine motion, mine dense-captioned clips for video pairs, and add transition supervision to teach how edits unfold. On the model side, we observe that pretrained text-to-video models possess editing capability, motivating a simplified design. Simple sequence concatenation for conditioning with light LoRA fine-tuning suffices to train a strong model. For control, we unify spatiotemporal control via a single mask mechanism and support optional reference images. Overall, EasyV2V works with flexible inputs, e.g., video+text, video+mask+text, video+mask+reference+text, and achieves state-of-the-art video editing results, surpassing concurrent and commercial systems. Project page: https://snap-research.github.io/easyv2v/ |
| title | EasyV2V: A High-quality Instruction-based Video Editing Framework |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.16920 |