Frequency Decoupled Domain-Irrelevant Feature Learning for Pan-Sharpening
IEEE Transactions on Circuits and Systems for Video Technology · 2025-02 · 35 (2) · 1237-1250
DOI: 10.1109/tcsvt.2024.3480950 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-02. Verfasst von Jie Zhang und 9 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: Natural Science Foundation of Anhui Province.
Abstract (Originalsprache)
Pan-sharpening aims to generate high-detail multi-spectral images (HRMS) through the fusion of panchromatic (PAN) and multi-spectral (MS) images. However, existing pan-sharpening methods often suffer from significant performance degradation when dealing with out-of-distribution data, as they assume the training and test datasets are independent and identically distributed. To overcome this challenge, we propose a novel frequency domain-irrelevant feature learning framework that exhibits exceptional generalization capabilities. Our approach involves parallel extraction and processing of domain-irrelevant information from the amplitude and phase components of the input images. Specifically, we design a frequency information separation module to extract the amplitude and phase components of the paired images. The learnable high-pass filter is then employed to eliminate domain-specific information from the amplitude spectrums. After that, we devised two specialized sub-networks (AFL-Net and PFL-Net) to perform targeted learning of the frequency domain-irrelevant information. This allows our method to effectively capture the complementary domain-irrelevant information contained in the amplitude and phase spectra of the images. Finally, the information fusion and restoration module dynamically adjusts the feature channel weights, enabling the network to output high-quality HRMS images. Through this frequency domain-irrelevant feature learning framework, our method balances generalization capability and network performance on the distribution of training dataset. Extensive experiments conducted on various satellite datasets demonstrate the effectiveness of our method for generalized pan-sharpening. Our proposed network outperforms state-of-the-art methods in terms of both quantitative metrics and visual quality, showcasing its superior ability to handle diverse, out-of-distribution data.
Förderung
- Natural Science Foundation of Anhui Province
Zitieren
APA
Zhang, J., Cao, K., Yan, K., Lin, Y., He, X., Wang, Y., Li, R., Xie, C., Zhang, J., & Zhou, M. (2025). Frequency Decoupled Domain-Irrelevant Feature Learning for Pan-Sharpening. IEEE Transactions on Circuits and Systems for Video Technology, 35(2), 1237-1250. https://doi.org/10.1109/tcsvt.2024.3480950
Vancouver
Zhang J, Cao K, Yan K, Lin Y, He X, Wang Y, et al. Frequency Decoupled Domain-Irrelevant Feature Learning for Pan-Sharpening. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(2):1237-1250. doi:10.1109/tcsvt.2024.3480950
BibTeX
@article{Zhang2025,
author = {Zhang, Jie and Cao, Ke and Yan, Keyu and Lin, Yunlong and He, Xuanhua and Wang, Yingying and Li, Rui and Xie, Chengjun and Zhang, Jun and Zhou, Man},
title = {Frequency Decoupled Domain-Irrelevant Feature Learning for Pan-Sharpening},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {2},
pages = {1237--1250},
doi = {10.1109/tcsvt.2024.3480950}
}
EUVIMED