EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HSSTN: A Hybrid Spectral–Structural Transformer Network for High-Fidelity Pansharpening

Weijie Kang, Yuan Feng, Yao Ding, Hongbo Xiang, Xiaobo Liu, Yaoming Cai

Remote Sensing · 23.09.2025 · 17 (19) · 3271

DOI: 10.3390/rs17193271 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 23.09.2025. Verfasst von Weijie Kang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Hubei Provincial Natural Science Foundation of China, China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pansharpening fuses multispectral (MS) and panchromatic (PAN) remote sensing images to generate outputs with high spatial resolution and spectral fidelity. Nevertheless, conventional methods relying primarily on convolutional neural networks or unimodal fusion strategies frequently fail to bridge the sensor modality gap between MS and PAN data. Consequently, spectral distortion and spatial degradation often occur, limiting high-precision downstream applications. To address these issues, this work proposes a Hybrid Spectral–Structural Transformer Network (HSSTN) that enhances multi-level collaboration through comprehensive modelling of spectral–structural feature complementarity. Specifically, the HSSTN implements a three-tier fusion framework. First, an asymmetric dual-stream feature extractor employs a residual block with channel attention (RBCA) in the MS branch to strengthen spectral representation, while a Transformer architecture in the PAN branch extracts high-frequency spatial details, thereby reducing modality discrepancy at the input stage. Subsequently, a target-driven hierarchical fusion network utilises progressive crossmodal attention across scales, ranging from local textures to multi-scale structures, to enable efficient spectral–structural aggregation. Finally, a novel collaborative optimisation loss function preserves spectral integrity while enhancing structural details. Comprehensive experiments conducted on QuickBird, GaoFen-2, and WorldView-3 datasets demonstrate that HSSTN outperforms existing methods in both quantitative metrics and visual quality. Consequently, the resulting images exhibit sharper details and fewer spectral artefacts, showcasing significant advantages in high-fidelity remote sensing image fusion.

Förderung

  • National Natural Science Foundation of China
  • Hubei Provincial Natural Science Foundation of China
  • China Postdoctoral Science Foundation
  • Postdoctoral Fellowship Program (Grade C) of China Postdoctoral Science Foundation
  • Joint Open Fund of the Research Platforms of School of Computer Science, China University of Geosciences, Wuhan

Zitieren

APA

Kang, W., Feng, Y., Ding, Y., Xiang, H., Liu, X., & Cai, Y. (2025). HSSTN: A Hybrid Spectral–Structural Transformer Network for High-Fidelity Pansharpening. Remote Sensing, 17(19), 3271. https://doi.org/10.3390/rs17193271

Vancouver

Kang W, Feng Y, Ding Y, Xiang H, Liu X, Cai Y. HSSTN: A Hybrid Spectral–Structural Transformer Network for High-Fidelity Pansharpening. Remote Sensing. 2025;17(19):3271. doi:10.3390/rs17193271

BibTeX
@article{Kang2025,
  author = {Kang, Weijie and Feng, Yuan and Ding, Yao and Xiang, Hongbo and Liu, Xiaobo and Cai, Yaoming},
  title = {HSSTN: A Hybrid Spectral–Structural Transformer Network for High-Fidelity Pansharpening},
  journal = {Remote Sensing},
  year = {2025},
  volume = {17},
  number = {19},
  pages = {3271},
  doi = {10.3390/rs17193271}
}
Kostenlos starten →