EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EBSFFormer: An Expert-Behavior-Guided Spatial–Frequency Collaborative Transformer for Remote Sensing Image Super-Resolution

Guangqi Xie, Caihao Guo, Shenggu Yuan, Siquan Yang, Wenbo Wu, Heyi Zhang

Remote Sensing · 13.11.2026 · 18 (22) · 3904

DOI: 10.3390/rs18223904 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 13.11.2026. Verfasst von Guangqi Xie und 5 weiteren Autor:innen. Die Arbeit nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, National Institute of Natural Hazards, the Ministry of Emergency Management of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing image super-resolution requires local detail and wider structural context. The mixture-of-experts (MoE) designs compared here select or combine expert outputs without explicitly passing behavior statistics to subsequent spatial–frequency restoration. We propose EBSFFormer, which aggregates routing preferences and response-weighted proportions within restoration groups and converts them into channel gains for later spatial and frequency branches. Heterogeneous experts and a content–cumulative-change router supply these statistics. We train on AID and evaluate on AID, DIOR, DOTA, and NWPU-RESISC45 under bicubic ×4 degradation. Across three AID training seeds, EBSFFormer obtains 31.2639 ± 0.0009 dB peak signal-to-noise ratio (PSNR), with mean improvements of 0.0121 dB over MambaIRv2 and 0.1037 dB over SwinIR. Single-checkpoint evaluation on NWPU without fine-tuning gives the highest Y-channel PSNR and structural similarity index (SSIM) among the compared methods and the third-lowest learned perceptual image patch similarity (LPIPS). Component ablations, red–green–blue (RGB) metrics, and ground-truth-referenced visual comparisons characterize the reconstruction gains. EBSFFormer has fewer parameters and lower mean latency than MambaIRv2, but the highest peak allocated memory in the runtime comparison.

Förderung

  • National Key R&D Program of China
  • National Institute of Natural Hazards, the Ministry of Emergency Management of China
  • National Natural Science Foundation of China
  • Scientific Research Foundation for Doctoral Program of Hubei University of Technology

Zitieren

APA

Xie, G., Guo, C., Yuan, S., Yang, S., Wu, W., & Zhang, H. (2026). EBSFFormer: An Expert-Behavior-Guided Spatial–Frequency Collaborative Transformer for Remote Sensing Image Super-Resolution. Remote Sensing, 18(22), 3904. https://doi.org/10.3390/rs18223904

Vancouver

Xie G, Guo C, Yuan S, Yang S, Wu W, Zhang H. EBSFFormer: An Expert-Behavior-Guided Spatial–Frequency Collaborative Transformer for Remote Sensing Image Super-Resolution. Remote Sensing. 2026;18(22):3904. doi:10.3390/rs18223904

BibTeX
@article{Xie2026,
  author = {Xie, Guangqi and Guo, Caihao and Yuan, Shenggu and Yang, Siquan and Wu, Wenbo and Zhang, Heyi},
  title = {EBSFFormer: An Expert-Behavior-Guided Spatial–Frequency Collaborative Transformer for Remote Sensing Image Super-Resolution},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {22},
  pages = {3904},
  doi = {10.3390/rs18223904}
}
Kostenlos starten →