EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CA-DDPM: Conditionally Embedded Attention-Aided Denoising Diffusion Probabilistic Model for High-Quality SAR Image Generation

Yang Zheng, Duhao Liu, Ruimin Li, Rongxu Wang, Junling Fan, Kaitai Guo, Jimin Liang

Remote Sensing · 15.06.2026 · 18 (12) · 1994

DOI: 10.3390/rs18121994 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 15.06.2026. Verfasst von Yang Zheng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning-based automatic target recognition (ATR) for synthetic aperture radar (SAR) imagery requires large quantities of high-quality annotated data, yet real SAR samples are costly and difficult to obtain. Existing generative adversarial network (GAN)-based SAR generation methods often suffer from limited authenticity and insufficient diversity. To address these issues, we propose CA-DDPM, a conditionally embedded attention-aided denoising diffusion probabilistic model (DDPM) for high-quality multi-category SAR image generation. CA-DDPM employs a unified conditional embedding that fuses time-step and category information, injected into a U-Net backbone through a feature-wise linear modulation (FiLM)-based mechanism to achieve step-aware and class-aware denoising. Attention blocks are further incorporated to enhance the modeling of structural dependencies and fine scattering details. To evaluate generation quality, we develop a three-dimensional assessment framework that jointly examines authenticity, diversity, and utility in ATR. Authenticity is quantified using local and global similarity metrics under a unified Hungarian-matched statistical procedure, together with an SAR-adapted Fréchet inception distance (SAR-FID). Diversity is assessed through inter-category feature clustering, an SAR Inception Score (SAR-IS), and a newly proposed intra-category grayscale histogram-based metric. Utility is evaluated by hybrid training experiments across multiple ATR models. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset demonstrate that CA-DDPM produces more realistic and diverse SAR images than representative GAN- and DDPM-based baselines, and it effectively improves downstream ATR performance through data augmentation.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zheng, Y., Liu, D., Li, R., Wang, R., Fan, J., Guo, K., & Liang, J. (2026). CA-DDPM: Conditionally Embedded Attention-Aided Denoising Diffusion Probabilistic Model for High-Quality SAR Image Generation. Remote Sensing, 18(12), 1994. https://doi.org/10.3390/rs18121994

Vancouver

Zheng Y, Liu D, Li R, Wang R, Fan J, Guo K, et al. CA-DDPM: Conditionally Embedded Attention-Aided Denoising Diffusion Probabilistic Model for High-Quality SAR Image Generation. Remote Sensing. 2026;18(12):1994. doi:10.3390/rs18121994

BibTeX
@article{Zheng2026,
  author = {Zheng, Yang and Liu, Duhao and Li, Ruimin and Wang, Rongxu and Fan, Junling and Guo, Kaitai and Liang, Jimin},
  title = {CA-DDPM: Conditionally Embedded Attention-Aided Denoising Diffusion Probabilistic Model for High-Quality SAR Image Generation},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {12},
  pages = {1994},
  doi = {10.3390/rs18121994}
}
Kostenlos starten →