Rethinking Nighttime Image Deraining via Learnable Color Space Transformation

TL;DR

This paper introduces a new high-quality dataset and a novel learnable color space transformation network for improved nighttime image deraining, effectively handling complex rain and illumination effects.

Contribution

It presents a high-quality benchmark dataset and a learnable color space transformation network with implicit illumination guidance for nighttime deraining.

Findings

The dataset HQ-NightRain offers higher realism and diversity.

CST-Net effectively removes complex rain in nighttime scenes.

The method outperforms existing deraining approaches on the new benchmark.

Abstract

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.