Saved in:
Bibliographic Details
Main Authors: Zhao, Enzhe, Guo, Zhichang, Li, Yao, Song, Fanghui, Wu, Boying
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.20179
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916810739154944
author Zhao, Enzhe
Guo, Zhichang
Li, Yao
Song, Fanghui
Wu, Boying
author_facet Zhao, Enzhe
Guo, Zhichang
Li, Yao
Song, Fanghui
Wu, Boying
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20179
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Progressive Alignment Degradation Learning for Pansharpening
Zhao, Enzhe
Guo, Zhichang
Li, Yao
Song, Fanghui
Wu, Boying
Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
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.
title Progressive Alignment Degradation Learning for Pansharpening
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
url https://arxiv.org/abs/2506.20179