GeoDiff-SAR: A Geometric Prior Guided Diffusion Model for SAR Image Generation
This addresses the challenge of generating realistic SAR images for remote sensing applications, offering a physics-guided approach to improve data quality and control, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of generating high-fidelity Synthetic Aperture Radar (SAR) images with precise control over geometric parameters like azimuth angles, by proposing GeoDiff-SAR, a diffusion model guided by geometric priors. The results show that data generated by GeoDiff-SAR enhances downstream classification accuracy, significantly improving recognition performance across different azimuth angles.
Synthetic Aperture Radar (SAR) imaging results are highly sensitive to observation geometries and the geometric parameters of targets. However, existing generative methods primarily operate within the image domain, neglecting explicit geometric information. This limitation often leads to unsatisfactory generation quality and the inability to precisely control critical parameters such as azimuth angles. To address these challenges, we propose GeoDiff-SAR, a geometric prior guided diffusion model for high-fidelity SAR image generation. Specifically, GeoDiff-SAR first efficiently simulates the geometric structures and scattering relationships inherent in real SAR imaging by calculating SAR point clouds at specific azimuths, which serves as a robust physical guidance. Secondly, to effectively fuse multi-modal information, we employ a feature fusion gating network based on Feature-wise Linear Modulation (FiLM) to dynamically regulate the weight distribution of 3D physical information, image control parameters, and textual description parameters. Thirdly, we utilize the Low-Rank Adaptation (LoRA) architecture to perform lightweight fine-tuning on the advanced Stable Diffusion 3.5 (SD3.5) model, enabling it to rapidly adapt to the distribution characteristics of the SAR domain. To validate the effectiveness of GeoDiff-SAR, extensive comparative experiments were conducted on real-world SAR datasets. The results demonstrate that data generated by GeoDiff-SAR exhibits high fidelity and effectively enhances the accuracy of downstream classification tasks. In particular, it significantly improves recognition performance across different azimuth angles, thereby underscoring the superiority of physics-guided generation.