Automatic Controllable Colorization via Imagination
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916197807685632 |
|---|---|
| author | Cong, Xiaoyan Wu, Yue Chen, Qifeng Lei, Chenyang |
| author_facet | Cong, Xiaoyan Wu, Yue Chen, Qifeng Lei, Chenyang |
| contents | We propose a framework for automatic colorization that allows for iterative editing and modifications. The core of our framework lies in an imagination module: by understanding the content within a grayscale image, we utilize a pre-trained image generation model to generate multiple images that contain the same content. These images serve as references for coloring, mimicking the process of human experts. As the synthesized images can be imperfect or different from the original grayscale image, we propose a Reference Refinement Module to select the optimal reference composition. Unlike most previous end-to-end automatic colorization algorithms, our framework allows for iterative and localized modifications of the colorization results because we explicitly model the coloring samples. Extensive experiments demonstrate the superiority of our framework over existing automatic colorization algorithms in editability and flexibility. Project page: https://xy-cong.github.io/imagine-colorization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_05661 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automatic Controllable Colorization via Imagination Cong, Xiaoyan Wu, Yue Chen, Qifeng Lei, Chenyang Computer Vision and Pattern Recognition We propose a framework for automatic colorization that allows for iterative editing and modifications. The core of our framework lies in an imagination module: by understanding the content within a grayscale image, we utilize a pre-trained image generation model to generate multiple images that contain the same content. These images serve as references for coloring, mimicking the process of human experts. As the synthesized images can be imperfect or different from the original grayscale image, we propose a Reference Refinement Module to select the optimal reference composition. Unlike most previous end-to-end automatic colorization algorithms, our framework allows for iterative and localized modifications of the colorization results because we explicitly model the coloring samples. Extensive experiments demonstrate the superiority of our framework over existing automatic colorization algorithms in editability and flexibility. Project page: https://xy-cong.github.io/imagine-colorization. |
| title | Automatic Controllable Colorization via Imagination |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.05661 |