Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restoration

2025-05-22

AI Summary

Severe image degradation arises from the coupled effects of multiple adverse weather conditions (e.g., rain, fog, snow) and nighttime halo artifacts, yet prior work has largely overlooked multi-weather coexistence in nighttime scenarios. Method: This paper presents the first systematic study of nighttime image restoration under concurrent weather degradations. We introduce AllWeatherNight—the first large-scale multi-weather nighttime image dataset—and propose ClearNight, a unified framework featuring: (i) illumination-aware degradation modeling; (ii) Retinex-based dual-prior-guided illumination-reflection decomposition; and (iii) a weather-aware dynamic synergy mechanism balancing shared and weather-specific representations. Contribution/Results: ClearNight achieves state-of-the-art performance on both synthetic and real-world benchmarks. Ablation studies confirm the necessity of AllWeatherNight and the efficacy of each component. This work establishes a new benchmark and an extensible paradigm for robust nighttime vision restoration under complex, multi-factor degradation.

Technology Category

• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data

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/mainpage.html

Problem

• Restoring nighttime images affected by multiple adverse weather conditions
• Handling intertwined weather degradations and flare effects in nighttime images
• Developing a unified framework for multi-weather nighttime image restoration

Innovation

• Uses Retinex-based dual priors for illumination and texture
• Introduces weather-aware dynamic specific-commonality collaboration method
• Develops AllWeatherNight dataset with illumination-aware degradation generation