Consistent Video Colorization via Palette Guidance
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917907722665984 |
|---|---|
| author | Wang, Han Zhang, Yuang Zhang, Yuhong Lu, Lingxiao Song, Li |
| author_facet | Wang, Han Zhang, Yuang Zhang, Yuhong Lu, Lingxiao Song, Li |
| contents | Colorization is a traditional computer vision task and it plays an important role in many time-consuming tasks, such as old film restoration. Existing methods suffer from unsaturated color and temporally inconsistency. In this paper, we propose a novel pipeline to overcome the challenges. We regard the colorization task as a generative task and introduce Stable Video Diffusion (SVD) as our base model. We design a palette-based color guider to assist the model in generating vivid and consistent colors. The color context introduced by the palette not only provides guidance for color generation, but also enhances the stability of the generated colors through a unified color context across multiple sequences. Experiments demonstrate that the proposed method can provide vivid and stable colors for videos, surpassing previous methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_19331 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Consistent Video Colorization via Palette Guidance Wang, Han Zhang, Yuang Zhang, Yuhong Lu, Lingxiao Song, Li Computer Vision and Pattern Recognition Colorization is a traditional computer vision task and it plays an important role in many time-consuming tasks, such as old film restoration. Existing methods suffer from unsaturated color and temporally inconsistency. In this paper, we propose a novel pipeline to overcome the challenges. We regard the colorization task as a generative task and introduce Stable Video Diffusion (SVD) as our base model. We design a palette-based color guider to assist the model in generating vivid and consistent colors. The color context introduced by the palette not only provides guidance for color generation, but also enhances the stability of the generated colors through a unified color context across multiple sequences. Experiments demonstrate that the proposed method can provide vivid and stable colors for videos, surpassing previous methods. |
| title | Consistent Video Colorization via Palette Guidance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.19331 |