EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dynamic Frequency Separated Fusion Network for RGB-T Semantic Segmentation

Shaochuan Zhao, Xiaotian Wang, Jiawei Jiang, Hefeng Yin, Bing Liu, Yong Zhou

Electronics · 05.11.2026 · 15 (21) · 5146

DOI: 10.3390/electronics15215146 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 05.11.2026. Verfasst von Shaochuan Zhao und 5 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, "Taihu Light" Science 446 and Technology Project of Wuxi.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RGB-T semantic segmentation fuses visible (RGB) and thermal infrared (TIR) images to enhance model robustness under complex lighting conditions. However, most existing methods employ unified fusion strategies in the spatial domain, limiting their ability to fully exploit the complementary characteristics of the two modalities across different frequency components. To address this issue, we propose a novel fusion model that achieves finer cross-modal collaboration through frequency-aware feature disentanglement and adaptive fusion mechanisms. Specifically, the model first enhances the multi-granularity representation of dual-modality features using attention mechanisms. The features are then transformed into the frequency domain, where a dynamic band disentanglement mechanism adaptively separates high-frequency details from low-frequency semantics based on the input content. A heterogeneous fusion pathway is further designed to differentially aggregate high- and low-frequency components, emphasizing cross-modal detail alignment in the high-frequency path and semantic consistency in the low-frequency path. The proposed model is evaluated on three widely-used RGB-T segmentation benchmarks, namely MFNet, PST900, and FMB, and achieves state-of-the-art performance, demonstrating its effectiveness and superiority.

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • "Taihu Light" Science 446 and Technology Project of Wuxi

Zitieren

APA

Zhao, S., Wang, X., Jiang, J., Yin, H., Liu, B., & Zhou, Y. (2026). Dynamic Frequency Separated Fusion Network for RGB-T Semantic Segmentation. Electronics, 15(21), 5146. https://doi.org/10.3390/electronics15215146

Vancouver

Zhao S, Wang X, Jiang J, Yin H, Liu B, Zhou Y. Dynamic Frequency Separated Fusion Network for RGB-T Semantic Segmentation. Electronics. 2026;15(21):5146. doi:10.3390/electronics15215146

BibTeX
@article{Zhao2026,
  author = {Zhao, Shaochuan and Wang, Xiaotian and Jiang, Jiawei and Yin, Hefeng and Liu, Bing and Zhou, Yong},
  title = {Dynamic Frequency Separated Fusion Network for RGB-T Semantic Segmentation},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {21},
  pages = {5146},
  doi = {10.3390/electronics15215146}
}
Kostenlos starten →