EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RAFnet: SAR Image Autofocusing via Range-Aware Attention and Multi-Scale Loss

Hua Wu iD, Yan Liu, Yunbai Qin iD, Haoran You, Zhuoxiang Lin

Sensors · 04.07.2026 · 26 (13) · 4270

DOI: 10.3390/s26134270 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 04.07.2026. Verfasst von Hua Wu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Information Engineering, Guangxi Normal University, Guilin 541004, China. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangxi Cyberspace Administration, 2025 Outstanding Talent Support Program of the Guangxi Cyberspace Administration.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Platform motion errors degrade SAR image quality in terms of severe defocusing and azimuth blurring. We propose a Range-aware Autofocus Network (RAFnet) by embedding a novel range-aware attention module into a progressive autofocus framework. The module exploits 1-D azimuth pooling to compress spatial features and extract high-SNR scattering components from the range dimension. Such features are further enriched via a light cross-channel interaction. To facilitate coarse-to-fine hierarchical learning, we develop a progressive multi-scale entropy loss which jointly optimizes the entire network. Experimental results on real SAR data show that the proposed approach captures high-level phase fluctuations accurately and effectively suppresses raw phase deviations and sidelobes. Quantitative results show that combining the attention module with multi-scale loss achieved a global spatial entropy of 9.8567 and contrast of 5.0091 in focused images. By extracting more accurate focus-oriented feature representations, we provide an effective solution for high-quality SAR auto-focusing.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismautofocusdeep learningsynthetic aperture radar (SAR)

Autor:innen und Institutionen

  • School of Electronic and Information Engineering, Guangxi Normal University, Guilin 541004, China.
  • College of Electronic and Information Engineering, Shenzhen University, Shenzhen 518000, China.

ORCID-Profile: Hua Wu, Yunbai Qin

Förderung

  • Guangxi Cyberspace Administration
  • 2025 Outstanding Talent Support Program of the Guangxi Cyberspace Administration

Zitieren

APA

Wu, H., Liu, Y., Qin, Y., You, H., & Lin, Z. (2026). RAFnet: SAR Image Autofocusing via Range-Aware Attention and Multi-Scale Loss. Sensors, 26(13), 4270. https://doi.org/10.3390/s26134270

Vancouver

Wu H, Liu Y, Qin Y, You H, Lin Z. RAFnet: SAR Image Autofocusing via Range-Aware Attention and Multi-Scale Loss. Sensors. 2026;26(13):4270. doi:10.3390/s26134270

BibTeX
@article{Wu2026,
  author = {Wu, Hua and Liu, Yan and Qin, Yunbai and You, Haoran and Lin, Zhuoxiang},
  title = {RAFnet: SAR Image Autofocusing via Range-Aware Attention and Multi-Scale Loss},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {13},
  pages = {4270},
  doi = {10.3390/s26134270}
}
Kostenlos starten →