Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restoration

TL;DR

This paper introduces a new dataset and a unified deep learning framework for restoring nighttime images affected by multiple weather conditions and lighting effects, achieving state-of-the-art results.

Contribution

It presents the AllWeatherNight dataset and the ClearNight restoration framework, incorporating weather-aware adaptation and dual priors for effective multi-weather nighttime image restoration.

Findings

Achieves state-of-the-art performance on synthetic and real-world images.

Validates the effectiveness of the AllWeatherNight dataset.

Demonstrates the benefits of weather-aware dynamic collaboration.

Abstract

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/