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

TL;DR

UtilityIR is a novel image restoration model that effectively handles multiple weather degradations by considering both weather type and severity, outperforming existing methods with fewer parameters.

Contribution

The paper introduces UtilityIR, a degradation-aware model that incorporates weather severity and type, using novel loss functions and attention mechanisms for improved all-in-one adverse weather removal.

Findings

Outperforms state-of-the-art methods on various weather removal tasks.

Capable of restoring images with unseen combined degradations.

Uses fewer model parameters while achieving superior results.

Abstract

All-in-one adverse weather removal is an emerging topic on image restoration, which aims to restore multiple weather degradations in an unified model, and the challenge are twofold. First, discover and handle the property of multi-domain in 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 limit 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 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 less model parameters. Proposed method even can restore unseen combined multiple degradation images, and modulate restoration level. Implementation code and pre-trained weights will be available at \url{https://github.com/fordevoted/UtilityIR}