DFSMamba: A Spatial–Frequency Collaborative Modeling Framework for Remote Sensing Image Super-Resolution
Remote Sensing · 09.06.2026 · 18 (12) · 1910
DOI: 10.3390/rs18121910 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 09.06.2026. Verfasst von Jie Yu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key R&D Program of Zhejiang, Cooperation Projects between the Ministry of Natural Resources and Jiangxi Province.
Abstract (Originalsprache)
Existing single-image super-resolution methods for remote sensing images suffer from insufficient global receptive fields, weak high-frequency texture recovery, and excessive computational complexity. To address these issues, this paper proposes DFSMamba, a novel spatial–frequency collaborative modeling framework. First, Semantic Continuous-Sparse Attention enhances semantic perception through dynamic chunking and sparse connections while maintaining linear complexity, effectively alleviating the semantic truncation problem caused by fixed window partitioning. Second, the Adaptive State-Space Module employs parallel forward and backward state-space model branches to achieve bidirectional long-range dependency modeling and introduces an activation-guided feature fusion mechanism to adaptively enhance semantically relevant regions. Third, the Discrete Fourier Transform Module maps images to the frequency domain, establishes a global lossless receptive field, and explicitly enhances high-frequency details, compensating for the insufficient utilization of frequency-domain information in pure spatial-domain methods. Experiments on five public datasets demonstrate that DFSMamba outperforms mainstream CNN, Transformer, and Mamba-based methods across ×2 to ×4 scales. On the AID×3 task, it achieves a PSNR of 31.48 dB, exceeding MambaIRv2 by 1.07 dB. Ablation studies verify the positive synergistic effect of the three modules, with the full configuration achieving a PSNR improvement of 0.85 dB over the single-module setup. Fine-grained category, multi-scale input, and loss function experiments further confirm its robustness and generalization capability, particularly in edge and texture detail reconstruction.
Förderung
- Key R&D Program of Zhejiang
- Cooperation Projects between the Ministry of Natural Resources and Jiangxi Province
Zitieren
APA
Yu, J., Li, H., Zheng, X., Zhong, C., & Sun, Q. (2026). DFSMamba: A Spatial–Frequency Collaborative Modeling Framework for Remote Sensing Image Super-Resolution. Remote Sensing, 18(12), 1910. https://doi.org/10.3390/rs18121910
Vancouver
Yu J, Li H, Zheng X, Zhong C, Sun Q. DFSMamba: A Spatial–Frequency Collaborative Modeling Framework for Remote Sensing Image Super-Resolution. Remote Sensing. 2026;18(12):1910. doi:10.3390/rs18121910
BibTeX
@article{Yu2026,
author = {Yu, Jie and Li, Hui and Zheng, Xiangyong and Zhong, Cheng and Sun, Qiao},
title = {DFSMamba: A Spatial–Frequency Collaborative Modeling Framework for Remote Sensing Image Super-Resolution},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {12},
pages = {1910},
doi = {10.3390/rs18121910}
}
EUVIMED