Rethinking Nighttime Image Deraining via Learnable Color Space Transformation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911221236629504 |
|---|---|
| author | Guan, Qiyuan Chen, Xiang Jin, Guiyue Jin, Jiyu Fan, Shumin Song, Tianyu Pan, Jinshan |
| author_facet | Guan, Qiyuan Chen, Xiang Jin, Guiyue Jin, Jiyu Fan, Shumin Song, Tianyu Pan, Jinshan |
| contents | Compared to daytime image deraining, nighttime image deraining poses significant challenges due to inherent complexities of nighttime scenarios and the lack of high-quality datasets that accurately represent the coupling effect between rain and illumination. In this paper, we rethink the task of nighttime image deraining and contribute a new high-quality benchmark, HQ-NightRain, which offers higher harmony and realism compared to existing datasets. In addition, we develop an effective Color Space Transformation Network (CST-Net) for better removing complex rain from nighttime scenes. Specifically, we propose a learnable color space converter (CSC) to better facilitate rain removal in the Y channel, as nighttime rain is more pronounced in the Y channel compared to the RGB color space. To capture illumination information for guiding nighttime deraining, implicit illumination guidance is introduced enabling the learned features to improve the model's robustness in complex scenarios. Extensive experiments show the value of our dataset and the effectiveness of our method. The source code and datasets are available at https://github.com/guanqiyuan/CST-Net. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17440 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rethinking Nighttime Image Deraining via Learnable Color Space Transformation Guan, Qiyuan Chen, Xiang Jin, Guiyue Jin, Jiyu Fan, Shumin Song, Tianyu Pan, Jinshan Computer Vision and Pattern Recognition Compared to daytime image deraining, nighttime image deraining poses significant challenges due to inherent complexities of nighttime scenarios and the lack of high-quality datasets that accurately represent the coupling effect between rain and illumination. In this paper, we rethink the task of nighttime image deraining and contribute a new high-quality benchmark, HQ-NightRain, which offers higher harmony and realism compared to existing datasets. In addition, we develop an effective Color Space Transformation Network (CST-Net) for better removing complex rain from nighttime scenes. Specifically, we propose a learnable color space converter (CSC) to better facilitate rain removal in the Y channel, as nighttime rain is more pronounced in the Y channel compared to the RGB color space. To capture illumination information for guiding nighttime deraining, implicit illumination guidance is introduced enabling the learned features to improve the model's robustness in complex scenarios. Extensive experiments show the value of our dataset and the effectiveness of our method. The source code and datasets are available at https://github.com/guanqiyuan/CST-Net. |
| title | Rethinking Nighttime Image Deraining via Learnable Color Space Transformation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.17440 |