晴朗之夜在前：迈向多天气条件下的夜间图像复原

Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restoration

May 22, 2025

作者: Yuetong Liu, Yunqiu Xu, Yang Wei, Xiuli Bi, Bin Xiao

cs.AI

摘要

恢复受多种恶劣天气条件影响的夜间图像是一个实际但尚未充分探索的研究课题，因为在现实世界中，多种天气条件常常与夜间的各种光照效果并存。本文首次探讨了具有挑战性的多天气夜间图像恢复任务，其中各类天气退化与光晕效应相互交织。为支持该研究，我们贡献了AllWeatherNight数据集，该数据集包含大规模高质量夜间图像，具有多样化的复合退化特征，这些图像是通过我们提出的光照感知退化生成方法合成的。此外，我们提出了ClearNight，一个统一的夜间图像恢复框架，能够一次性有效去除复杂的退化。具体而言，ClearNight提取基于Retinex的双重先验，并明确引导网络分别关注不均匀光照区域和内在纹理内容，从而提升夜间场景下的恢复效果。为了更好地表征多种天气退化的共性与独特性，我们引入了一种天气感知的动态特异性-共性协作方法，该方法识别天气退化并自适应选择与特定天气类型相关的最优候选单元。我们的ClearNight在合成图像和真实世界图像上均实现了最先进的性能。全面的消融实验验证了AllWeatherNight数据集的必要性以及ClearNight的有效性。项目页面：https://henlyta.github.io/ClearNight/mainpage.html

English

Restoring nighttime images affected by multiple adverse weather conditions is a practical yet under-explored research problem, as multiple weather conditions often coexist in the real world alongside various lighting effects at night. This paper first explores the challenging multi-weather nighttime image restoration task, where various types of weather degradations are intertwined with flare effects. To support the research, we contribute the AllWeatherNight dataset, featuring large-scale high-quality nighttime images with diverse compositional degradations, synthesized using our introduced illumination-aware degradation generation. Moreover, we present ClearNight, a unified nighttime image restoration framework, which effectively removes complex degradations in one go. Specifically, ClearNight extracts Retinex-based dual priors and explicitly guides the network to focus on uneven illumination regions and intrinsic texture contents respectively, thereby enhancing restoration effectiveness in nighttime scenarios. In order to better represent the common and unique characters of multiple weather degradations, we introduce a weather-aware dynamic specific-commonality collaboration method, which identifies weather degradations and adaptively selects optimal candidate units associated with specific weather types. Our ClearNight achieves state-of-the-art performance on both synthetic and real-world images. Comprehensive ablation experiments validate the necessity of AllWeatherNight dataset as well as the effectiveness of ClearNight. Project page: https://henlyta.github.io/ClearNight/mainpage.html