EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

SCFusion: Spatial-Channel Cross-Frequency Guided Fusion Network for Infrared–Visible Image Object Detection

Guoxia Xu, Yulong Sun, Kang Chen, Yufeng Yu, Lizhen Deng, Hu Zhu

Mathematics · 2026-03-12 · 14 (6) · 969

DOI: 10.3390/math14060969 ↗

At a glance

Journal article in Mathematics, published online on 2026-03-12. Written by Guoxia Xu and 5 co-authors. Cited 1 times so far (Crossref); 42 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, Postdoctoral Fellowship Program of China Postdoctoral Science Foundation, Jiangsu Funding Program for Excellent Postdoctoral Talent.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

While infrared–visible image object detection exhibits advantages in complex scenarios, existing methods still suffer from issues such as static frequency-domain modeling, severe cross-modal interference, and insufficient local detail perception. To address these problems, this paper proposes an infrared and visible image object detection based on a spatial-channel cross-frequency guided fusion network. First, we construct a frequency residual selective transformer to realize local inductive bias and a global receptive field for infrared and visible image feature extraction. Furthermore, the spatial-channel frequency fusion mechanism based on the Homogeneous Frequency Refined Block and the Heterogeneous Spatial-Channel Frequency Fusion Block is proposed to achieve modality-consistent feature fusion. Finally, the frequency reconstruction guided decoder selects high-frequency components to sharpen object boundaries. The SCFusion network was evaluated on four public benchmark datasets (VT821, VT1000, VT5000, and VI-RGBT1500), with test sets containing 411, 400, 2500, and 600 pairs of infrared–visible images, respectively. Following the standard training and testing protocol, the network achieved Mean Absolute Error (MAE) scores of 0.025 (VT821), 0.016 (VT1000), 0.023 (VT5000), and 0.020 (VI-RGBT1500).

Funding

  • National Natural Science Foundation of China
  • Postdoctoral Fellowship Program of China Postdoctoral Science Foundation
  • Jiangsu Funding Program for Excellent Postdoctoral Talent
  • Natural Science Research Start-up Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications

Cite

APA

Xu, G., Sun, Y., Chen, K., Yu, Y., Deng, L., & Zhu, H. (2026). SCFusion: Spatial-Channel Cross-Frequency Guided Fusion Network for Infrared–Visible Image Object Detection. Mathematics, 14(6), 969. https://doi.org/10.3390/math14060969

Vancouver

Xu G, Sun Y, Chen K, Yu Y, Deng L, Zhu H. SCFusion: Spatial-Channel Cross-Frequency Guided Fusion Network for Infrared–Visible Image Object Detection. Mathematics. 2026;14(6):969. doi:10.3390/math14060969

BibTeX
@article{Xu2026,
  author = {Xu, Guoxia and Sun, Yulong and Chen, Kang and Yu, Yufeng and Deng, Lizhen and Zhu, Hu},
  title = {SCFusion: Spatial-Channel Cross-Frequency Guided Fusion Network for Infrared–Visible Image Object Detection},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {6},
  pages = {969},
  doi = {10.3390/math14060969}
}
Start for free →