Progressive Alignment Degradation Learning for Pansharpening

2025-06-25

AI Summary

Wald’s protocol inaccurately models the true degradation process in deep pansharpening, limiting model generalization. To address this, we propose a Progressive Alignment Degradation Learning (PADL) framework. First, we design the Progressive Alignment Degradation Module (PADM), which jointly optimizes PAlignNet and PDegradeNet in an alternating iterative manner to adaptively approximate the real-world degradation process. Second, we introduce HFreqdiff—a high-frequency reconstruction method integrating diffusion modeling, frequency-selective modules (CFB/BACM), and backward-process calibration for precise recovery of fine spatial details. Extensive experiments on multiple remote sensing benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches in both spatial enhancement and spectral fidelity. Ablation studies validate the effectiveness and necessity of each component.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multimodal Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

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.

Problem

• Inaccurate degradation patterns limit pansharpening model generalization
• Adaptive degradation learning without predefined operators is needed
• Effective integration of panchromatic and multispectral images enhances quality

Innovation

• Progressive Alignment Degradation Module adaptively learns degradation
• HFreqdiff embeds high-frequency details via diffusion framework
• CFB and BACM enable frequency-selective detail extraction