Always Clear Days: Degradation Type and Severity Aware All-in-One Adverse Weather Removal

Abstract

All-in-one adverse weather removal is an emerging topic on image restoration, which aims to restore multiple weather degradations in a unified model, and the challenges are twofold. First, discover and handle the properties of the multi-domain in the target distribution formed by multiple weather conditions. Second, design efficient and effective operations for different degradations. To resolve this problem, most prior works focus on the multi-domain caused by different weather types. Inspired by inter&intra-domain adaptation literature, we observe that not only weather type but also weather severity introduce multi-domain within each weather type domain, which is ignored by previous methods and further limits their performance. To this end, we propose a degradation type and severity aware model, called UtilityIR, for blind all-in-one bad weather image restoration. To extract weather information from a single image, we propose a novel Marginal Quality Ranking Loss (MQRL) and utilize Contrastive Loss (CL) to guide weather severity and type extraction, and leverage a bag of novel techniques such as Multi-Head Cross Attention (MHCA) and Local-Global Adaptive Instance Normalization (LG-AdaIN) to efficiently restore spatial varying weather degradation. The proposed method can outperform the state-of-the-art methods subjectively and objectively on different weather removal tasks with a large margin, and enjoy fewer model parameters. The proposed method can even restore previously unseen combined multiple degradation images, and modulate restoration level. Implementation code and pre-trained weights will be available at https://github.com/fordevoted/UtilityIR.

Keywords

• Adverse weather removal
• all-in-one image restoration
• degradation estimation
• deraining
• dehazing
• desnowing