Neural Degradation Representation Learning for All-In-One Image Restoration

TL;DR

This paper introduces a neural degradation representation learning framework for all-in-one image restoration, effectively handling multiple degradation types by capturing their underlying characteristics and enabling adaptive processing.

Contribution

It proposes a neural degradation representation (NDR) that decomposes various degradations, along with modules for recognition and utilization, and a bidirectional optimization strategy for improved multi-degradation restoration.

Findings

Effective on multiple degradation types including noise, haze, rain, and downsampling.

Demonstrates strong generalization capability across different degradations.

Outperforms existing methods in restoration quality and adaptability.

Abstract

Existing methods have demonstrated effective performance on a single degradation type. In practical applications, however, the degradation is often unknown, and the mismatch between the model and the degradation will result in a severe performance drop. In this paper, we propose an all-in-one image restoration network that tackles multiple degradations. Due to the heterogeneous nature of different types of degradations, it is difficult to process multiple degradations in a single network. To this end, we propose to learn a neural degradation representation (NDR) that captures the underlying characteristics of various degradations. The learned NDR decomposes different types of degradations adaptively, similar to a neural dictionary that represents basic degradation components. Subsequently, we develop a degradation query module and a degradation injection module to effectively recognize and utilize the specific degradation based on NDR, enabling the all-in-one restoration ability for multiple degradations. Moreover, we propose a bidirectional optimization strategy to effectively drive NDR to learn the degradation representation by optimizing the degradation and restoration processes alternately. Comprehensive experiments on representative types of degradations (including noise, haze, rain, and downsampling) demonstrate the effectiveness and generalization capability of our method.