Physically Interpretable Multi-Degradation Image Restoration via Deep Unfolding and Explainable Convolution

TL;DR

This paper introduces InterIR, a deep unfolding network with explainable modules for multi-degradation image restoration, emphasizing interpretability and adaptability in handling complex real-world image degradations.

Contribution

The paper presents a novel deep unfolding framework with explainable convolution modules, improving interpretability and performance in multi-degradation image restoration tasks.

Findings

Effective multi-degradation restoration performance

High interpretability of the network modules

Competitive results on single-degradation tasks

Abstract

Although image restoration has advanced significantly, most existing methods target only a single type of degradation. In real-world scenarios, images often contain multiple degradations simultaneously, such as rain, noise, and haze, requiring models capable of handling diverse degradation types. Moreover, methods that improve performance through module stacking often suffer from limited interpretability. In this paper, we propose a novel interpretability-driven approach for multi-degradation image restoration, built upon a deep unfolding network that maps the iterative process of a mathematical optimization algorithm into a learnable network structure. Specifically, we employ an improved second-order semi-smooth Newton algorithm to ensure that each module maintains clear physical interpretability. To further enhance interpretability and adaptability, we design an explainable convolution module inspired by the human brain's flexible information processing and the intrinsic characteristics of images, allowing the network to flexibly leverage learned knowledge and autonomously adjust parameters for different input. The resulting tightly integrated architecture, named InterIR, demonstrates excellent performance in multi-degradation restoration while remaining highly competitive on single-degradation tasks.