Frequency-enhanced diffusion prior network for joint SAR image despeckling and super-resolution
Measurement Science and Technology · 14.08.2026 · 37 (32) · 326112
DOI: 10.1088/1361-6501/ae8686 ↗Kurz gefasst
Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 12.08.2026. Verfasst von Cao Wenqiang und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Gefördert von: Xijing University Research Fund, Shaanxi Provincial Key R&D Program.
Abstract (Originalsprache)
Synthetic aperture radar (SAR) image enhancement faces inherent difficulties in simultaneous speckle suppression and structural detail preservation, severely limiting the performance of conventional methods in high-precision remote sensing tasks. This paper proposes a novel two-stage cascaded deep learning framework for high-quality SAR image reconstruction, which sequentially integrates a window-based Transformer denoising subnet and a diffusion-driven super-resolution subnet via a learnable projection matrix. To address the coupled degradation of speckle noise, imaging blurring, and structural loss, four dedicated designs are adopted, including a projection-coupled serial architecture for joint optimization and lightweight parameter deployment (24.3% parameter reduction), a Frequency Enhancement Module for high-frequency detail recovery, an Adaptive Noise Scheduler for robust diffusion adjustment under complex textures and low-contrast conditions, and Meta Residual Connections for stable deep feature propagation. Quantitative experiments on the FAIR-CSAR-V1.0 ×4 super-resolution benchmark demonstrate that the proposed method achieves state-of-the-art performance with 19.26 dB PSNR, 0.3502 SSIM, 2.23 ENL, and 2.26 RadRes. Our method outperforms the baseline model by 5.71% in PSNR and 30.4% in SSIM, and surpasses existing SOTA methods by 31.9%, 108.2%, 105.6%, and 27.3% in four metrics, respectively, with prominent gains mainly obtained in challenging noisy and low-contrast SAR regions. Ablation studies validate the efficacy of each component. The proposed framework provides an effective lightweight solution for high-precision SAR reconstruction applicable to military reconnaissance, geological exploration, and disaster monitoring.
Förderung
- Xijing University Research Fund
- Shaanxi Provincial Key R&D Program
Zitieren
APA
Wenqiang, C., Yarong, C., Rui, Z., & Peng, C. (2026). Frequency-enhanced diffusion prior network for joint SAR image despeckling and super-resolution. Measurement Science and Technology, 37(32), 326112. https://doi.org/10.1088/1361-6501/ae8686
Vancouver
Wenqiang C, Yarong C, Rui Z, Peng C. Frequency-enhanced diffusion prior network for joint SAR image despeckling and super-resolution. Measurement Science and Technology. 2026;37(32):326112. doi:10.1088/1361-6501/ae8686
BibTeX
@article{Wenqiang2026,
author = {Wenqiang, Cao and Yarong, Chen and Rui, Zhu and Peng, Chu},
title = {Frequency-enhanced diffusion prior network for joint SAR image despeckling and super-resolution},
journal = {Measurement Science and Technology},
year = {2026},
volume = {37},
number = {32},
pages = {326112},
doi = {10.1088/1361-6501/ae8686}
}
EUVIMED