A Progressive Image Restoration Network for High-order Degradation Imaging in Remote Sensing

2024-12-10

arXiv.org

AI Summary

To address the insufficient modeling of high-order degradations in remote sensing images and the limited interpretability of existing deep learning methods, this paper proposes HDI-PRNet, a progressive restoration network. Grounded in physics-driven degradation theory, HDI-PRNet jointly models noise, blur, and super-resolution degradation in a staged, cooperative manner. It is the first to integrate high-order degradation modeling with interpretable unrolling networks, incorporating proximal mapping prior learning, Neumann series expansion, and dual-domain (spatial–frequency) degradation modeling—thereby unifying architectural transparency with mathematical interpretability. Extensive experiments on both synthetic and real-world remote sensing datasets demonstrate that HDI-PRNet achieves state-of-the-art performance in PSNR, SSIM, and visual quality, significantly outperforming mainstream approaches.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Recently, deep learning methods have gained remarkable achievements in the field of image restoration for remote sensing (RS). However, most existing RS image restoration methods focus mainly on conventional first-order degradation models, which may not effectively capture the imaging mechanisms of remote sensing images. Furthermore, many RS image restoration approaches that use deep learning are often criticized for their lacks of architecture transparency and model interpretability. To address these problems, we propose a novel progressive restoration network for high-order degradation imaging (HDI-PRNet), to progressively restore different image degradation. HDI-PRNet is developed based on the theoretical framework of degradation imaging, offering the benefit of mathematical interpretability within the unfolding network. The framework is composed of three main components: a module for image denoising that relies on proximal mapping prior learning, a module for image deblurring that integrates Neumann series expansion with dual-domain degradation learning, and a module for super-resolution. Extensive experiments demonstrate that our method achieves superior performance on both synthetic and real remote sensing images.

Problem

• Addresses high-order degradation in remote sensing images
• Improves architecture transparency and model interpretability
• Proposes a progressive restoration network for multiple degradations

Innovation

• Progressive network for high-order degradation restoration
• Markov properties and MAP estimation framework
• Dual-domain degradation learning for deblurring