提出新数据集与可学习色彩转换网络，提升夜间雨滴去除效果
Rethinking Nighttime Image Deraining via Learnable Color Space Transformation
- 设计可学习色彩转换器，在亮度通道更有效去雨
- 构建高质量夜间雨景数据集，增强真实感与和谐性
- 引入隐式光照引导，提升复杂场景鲁棒性，适合夜视应用
相比白天去雨，夜间去雨因场景固有复杂性和缺乏准确反映雨与光照耦合效应的高质量数据集而面临更大挑战。本文重新审视夜间去雨任务，构建了一个新基准数据集HQ-NightRain，其在和谐性与真实性上优于现有数据集。同时提出一种有效的色彩空间变换网络（CST-Net），通过可学习的色彩空间转换器（CSC）在亮度通道（Y）中更优地实现去雨，因夜间雨滴在亮度通道更显著。为捕捉光照信息以指导去雨，引入隐式光照引导机制，使模型特征更具鲁棒性。大量实验验证了数据集和方法的有效性。代码与数据集已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。