Rethinking Nighttime Image Deraining via Learnable Color Space Transformation
This work addresses the problem of enhancing image quality in low-light conditions for applications like surveillance and autonomous driving, but it is incremental as it builds on existing deraining methods with specific nighttime adaptations.
The authors tackled nighttime image deraining by introducing a new high-quality benchmark dataset, HQ-NightRain, and a Color Space Transformation Network (CST-Net) that uses a learnable color space converter and implicit illumination guidance, achieving improved performance in removing rain from nighttime scenes.
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.