Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910871446355968 |
|---|---|
| author | Zi, Bojia Ruan, Penghui Chen, Marco Qi, Xianbiao Hao, Shaozhe Zhao, Shihao Huang, Youze Liang, Bin Xiao, Rong Wong, Kam-Fai |
| author_facet | Zi, Bojia Ruan, Penghui Chen, Marco Qi, Xianbiao Hao, Shaozhe Zhao, Shihao Huang, Youze Liang, Bin Xiao, Rong Wong, Kam-Fai |
| contents | Recent advancements in video generation have spurred the development of video editing techniques, which can be divided into inversion-based and end-to-end methods. However, current video editing methods still suffer from several challenges. Inversion-based methods, though training-free and flexible, are time-consuming during inference, struggle with fine-grained editing instructions, and produce artifacts and jitter. On the other hand, end-to-end methods, which rely on edited video pairs for training, offer faster inference speeds but often produce poor editing results due to a lack of high-quality training video pairs. In this paper, to close the gap in end-to-end methods, we introduce Señorita-2M, a high-quality video editing dataset. Señorita-2M consists of approximately 2 millions of video editing pairs. It is built by crafting four high-quality, specialized video editing models, each crafted and trained by our team to achieve state-of-the-art editing results. We also propose a filtering pipeline to eliminate poorly edited video pairs. Furthermore, we explore common video editing architectures to identify the most effective structure based on current pre-trained generative model. Extensive experiments show that our dataset can help to yield remarkably high-quality video editing results. More details are available at https://senorita-2m-dataset.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06734 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists Zi, Bojia Ruan, Penghui Chen, Marco Qi, Xianbiao Hao, Shaozhe Zhao, Shihao Huang, Youze Liang, Bin Xiao, Rong Wong, Kam-Fai Computer Vision and Pattern Recognition Recent advancements in video generation have spurred the development of video editing techniques, which can be divided into inversion-based and end-to-end methods. However, current video editing methods still suffer from several challenges. Inversion-based methods, though training-free and flexible, are time-consuming during inference, struggle with fine-grained editing instructions, and produce artifacts and jitter. On the other hand, end-to-end methods, which rely on edited video pairs for training, offer faster inference speeds but often produce poor editing results due to a lack of high-quality training video pairs. In this paper, to close the gap in end-to-end methods, we introduce Señorita-2M, a high-quality video editing dataset. Señorita-2M consists of approximately 2 millions of video editing pairs. It is built by crafting four high-quality, specialized video editing models, each crafted and trained by our team to achieve state-of-the-art editing results. We also propose a filtering pipeline to eliminate poorly edited video pairs. Furthermore, we explore common video editing architectures to identify the most effective structure based on current pre-trained generative model. Extensive experiments show that our dataset can help to yield remarkably high-quality video editing results. More details are available at https://senorita-2m-dataset.github.io. |
| title | Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.06734 |