EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Scale Frequency-Aware Representation Learning for Infrared and Visible Image Fusion

Chuanwen Hu, Zheyi Hu, Chuan Xu, Zhina Song, Liye Mei

Remote Sensing · 15.04.2026 · 18 (8) · 1178

DOI: 10.3390/rs18081178 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 15.04.2026. Verfasst von Chuanwen Hu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hubei Provincial Natural Science Foundation of China, Science and Technology Research Project of Education Department of Hubei Province, Natural Science Foundation of China under Grant.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Infrared and visible image fusion aims to integrate complementary information from heterogeneous sensors for remote sensing and Earth-observation applications. To achieve a better balance between global contextual modeling and local structural preservation, we propose MSF-Net, a multi-scale frequency-aware fusion network with a hierarchical design. The proposed framework consists of two main stages: multi-scale feature extraction with frequency-domain interaction and hierarchical cross-modal fusion. Specifically, a hybrid spatial-frequency encoding block (HSFEB) is designed as the basic building unit, which combines a spatial-frequency interaction module (SFIM) for global context aggregation in the frequency domain and a structure-guided feature refinement module (SGFRM) for preserving local structural details. In addition, a hierarchical feature fusion module (HFFM) is introduced to progressively integrate cross-modal and cross-scale features in a coarse-to-fine manner. A joint loss function, composed of intensity and structural constraints, is adopted to supervise the fusion process. Extensive experiments on three public benchmarks, MSRS, M3FD, and TNO, demonstrate that MSF-Net achieves superior performance over nine SOTA methods in both qualitative and quantitative evaluations. The results show that the proposed method effectively enhances thermal targets, preserves structural details, and maintains good visual naturalness under diverse remote-sensing scenarios.

Förderung

  • Hubei Provincial Natural Science Foundation of China
  • Science and Technology Research Project of Education Department of Hubei Province
  • Natural Science Foundation of China under Grant
  • Graduate Education Reform Research Project of Hubei University of Technology
  • Hubei Province Young Science and Technology Talent Morning Hight Lift Project

Zitieren

APA

Hu, C., Hu, Z., Xu, C., Song, Z., & Mei, L. (2026). Multi-Scale Frequency-Aware Representation Learning for Infrared and Visible Image Fusion. Remote Sensing, 18(8), 1178. https://doi.org/10.3390/rs18081178

Vancouver

Hu C, Hu Z, Xu C, Song Z, Mei L. Multi-Scale Frequency-Aware Representation Learning for Infrared and Visible Image Fusion. Remote Sensing. 2026;18(8):1178. doi:10.3390/rs18081178

BibTeX
@article{Hu2026,
  author = {Hu, Chuanwen and Hu, Zheyi and Xu, Chuan and Song, Zhina and Mei, Liye},
  title = {Multi-Scale Frequency-Aware Representation Learning for Infrared and Visible Image Fusion},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {8},
  pages = {1178},
  doi = {10.3390/rs18081178}
}
Kostenlos starten →