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

2025-11-13

AI Summary

Real-world images often suffer from multiple degradations—such as rain, fog, noise, and haze—yet existing methods typically address only a single degradation and lack physical interpretability. To address this, we propose InterIR, a physically grounded deep unfolding framework that explicitly models a second-order semismooth Newton optimization process as a learnable network module, ensuring each layer retains clear physical meaning. Central to InterIR is a brain-inspired, interpretable convolution operator that enables parameter adaptation and dynamic incorporation of prior knowledge. By jointly modeling multiple degradations within a unified, physics-aware architecture, InterIR achieves state-of-the-art performance on both single- and multi-degradation image restoration tasks. Moreover, it significantly enhances model transparency, generalizability across diverse degradation scenarios, and practical deployability in real-world applications.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Addresses multi-degradation image restoration handling rain, noise, and haze simultaneously
• Improves interpretability of deep learning models through mathematical optimization mapping
• Enhances model adaptability using explainable convolution inspired by human brain processing

Innovation

• Deep unfolding network for multi-degradation restoration
• Second-order semi-smooth Newton algorithm for interpretability
• Explainable convolution module with autonomous parameter adjustment