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

TL;DR

This paper introduces HDI-PRNet, a progressive deep learning framework for remote sensing image restoration that models high-order degradation processes with interpretability and outperforms existing methods.

Contribution

The paper presents a novel progressive restoration network based on degradation imaging theory, Markov properties, and MAP estimation, enhancing interpretability and effectiveness in high-order degradation restoration.

Findings

Achieves superior performance on synthetic and real RS images

Effectively models high-order degradation processes

Provides a transparent, mathematically interpretable framework

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, also Markov properties of the high-order degradation process and Maximum a posteriori (MAP) estimation, 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.