Unifying Physically-Informed Weather Priors in A Single Model for Image Restoration Across Multiple Adverse Weather Conditions

2026-05-13

AI Summary

Existing image restoration methods struggle to effectively model the distance-dependent physical degradation processes under diverse adverse weather conditions, leading to limited performance. This work proposes a unified physical imaging model that explicitly integrates near-range precipitation particle occlusion with far-range haze-like scattering effects. To enhance feature representation, we design a weather prior–guided deep network that jointly estimates an occlusion map and a transmission map. Our approach is the first to incorporate physical priors from multiple weather conditions into a single end-to-end framework, enabling cross-weather generalization for image restoration. Experiments demonstrate that the proposed method significantly outperforms current state-of-the-art techniques across various adverse weather scenarios, achieving both high restoration quality and strong robustness.

Abstract

Image restoration under multiple adverse weather conditions aims to develop a single model to recover the underlying scene with high visibility. Weather-related artifacts vary with the particle's distance to the camera according to the established scene visibility analysis, where close and faraway regions are more affected by falling drops and fog effects, respectively. Existing methods fail to consider this weather-specific physical visual process; thus, the restoration performance is limited. In this work, we analyze the common visual factors in adverse weather conditions and present a unified imaging model that considers the individually visible particles and fog-like aggregate scattering effects. Further, we design a novel weather-prior-based network, which leverages the weather-related prior information to help recover the scene by enhancing the features using the estimated occlusion and transmission. Experimental results in multiple adverse scenarios show the superiority of our method against state-of-the-art methods.

Problem

• image restoration
• adverse weather conditions
• weather priors
• scene visibility
• physical imaging model

Innovation

• physically-informed priors
• unified imaging model
• adverse weather restoration
• occlusion and transmission estimation
• multi-weather image restoration