Progressive Alignment Degradation Learning for Pansharpening

TL;DR

This paper introduces a novel deep learning framework for pansharpening that adaptively learns degradation processes and enhances image details, overcoming limitations of traditional synthetic data protocols.

Contribution

It proposes the Progressive Alignment Degradation Module (PADM) and HFreqdiff, enabling more accurate degradation modeling and high-frequency detail integration without relying on predefined operators.

Findings

Outperforms state-of-the-art pansharpening methods in quality metrics.

Effectively learns real-world degradation patterns.

Enhances spatial sharpness and detail preservation.

Abstract

Deep learning-based pansharpening has been shown to effectively generate high-resolution multispectral (HRMS) images. To create supervised ground-truth HRMS images, synthetic data generated using the Wald protocol is commonly employed. This protocol assumes that networks trained on artificial low-resolution data will perform equally well on high-resolution data. However, well-trained models typically exhibit a trade-off in performance between reduced-resolution and full-resolution datasets. In this paper, we delve into the Wald protocol and find that its inaccurate approximation of real-world degradation patterns limits the generalization of deep pansharpening models. To address this issue, we propose the Progressive Alignment Degradation Module (PADM), which uses mutual iteration between two sub-networks, PAlignNet and PDegradeNet, to adaptively learn accurate degradation processes without relying on predefined operators. Building on this, we introduce HFreqdiff, which embeds high-frequency details into a diffusion framework and incorporates CFB and BACM modules for frequency-selective detail extraction and precise reverse process learning. These innovations enable effective integration of high-resolution panchromatic and multispectral images, significantly enhancing spatial sharpness and quality. Experiments and ablation studies demonstrate the proposed method's superior performance compared to state-of-the-art techniques.