Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.07826 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917148168814592 |
|---|---|
| author | He, Haoyang Wang, Jie Zhang, Jiangning Xue, Zhucun Bu, Xingyuan Yang, Qiangpeng Wen, Shilei Xie, Lei |
| author_facet | He, Haoyang Wang, Jie Zhang, Jiangning Xue, Zhucun Bu, Xingyuan Yang, Qiangpeng Wen, Shilei Xie, Lei |
| contents | The quality and diversity of instruction-based image editing datasets are continuously increasing, yet large-scale, high-quality datasets for instruction-based video editing remain scarce. To address this gap, we introduce OpenVE-3M, an open-source, large-scale, and high-quality dataset for instruction-based video editing. It comprises two primary categories: spatially-aligned edits (Global Style, Background Change, Local Change, Local Remove, Local Add, and Subtitles Edit) and non-spatially-aligned edits (Camera Multi-Shot Edit and Creative Edit). All edit types are generated via a meticulously designed data pipeline with rigorous quality filtering. OpenVE-3M surpasses existing open-source datasets in terms of scale, diversity of edit types, instruction length, and overall quality. Furthermore, to address the lack of a unified benchmark in the field, we construct OpenVE-Bench, containing 431 video-edit pairs that cover a diverse range of editing tasks with three key metrics highly aligned with human judgment. We present OpenVE-Edit, a 5B model trained on our dataset that demonstrates remarkable efficiency and effectiveness by setting a new state-of-the-art on OpenVE-Bench, outperforming all prior open-source models including a 14B baseline. Project page is at https://lewandofskee.github.io/projects/OpenVE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_07826 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing He, Haoyang Wang, Jie Zhang, Jiangning Xue, Zhucun Bu, Xingyuan Yang, Qiangpeng Wen, Shilei Xie, Lei Computer Vision and Pattern Recognition The quality and diversity of instruction-based image editing datasets are continuously increasing, yet large-scale, high-quality datasets for instruction-based video editing remain scarce. To address this gap, we introduce OpenVE-3M, an open-source, large-scale, and high-quality dataset for instruction-based video editing. It comprises two primary categories: spatially-aligned edits (Global Style, Background Change, Local Change, Local Remove, Local Add, and Subtitles Edit) and non-spatially-aligned edits (Camera Multi-Shot Edit and Creative Edit). All edit types are generated via a meticulously designed data pipeline with rigorous quality filtering. OpenVE-3M surpasses existing open-source datasets in terms of scale, diversity of edit types, instruction length, and overall quality. Furthermore, to address the lack of a unified benchmark in the field, we construct OpenVE-Bench, containing 431 video-edit pairs that cover a diverse range of editing tasks with three key metrics highly aligned with human judgment. We present OpenVE-Edit, a 5B model trained on our dataset that demonstrates remarkable efficiency and effectiveness by setting a new state-of-the-art on OpenVE-Bench, outperforming all prior open-source models including a 14B baseline. Project page is at https://lewandofskee.github.io/projects/OpenVE. |
| title | OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.07826 |