DiffuSAR: Frequency Domain-Aware Diffusion Model for SAR Image Generation

In recent years, deep learning-based synthetic aperture radar (SAR) image detection, recognition, and segmentation models achieve remarkable accuracy when trained on large amounts of SAR image samples. However, the acquisition of SAR images tends to be costly. A practical approach to address this issue involves the use of artificially generated training samples to supplement the dataset. Current SAR image generation methods based on generative adversarial networks have issues with generation fidelity and are challenge to converge. Moreover, most of these methods only consider the spatial domain of SAR images without exploring the characteristics of their frequency domain. To tackle the aforementioned problems, we proposed a lightweight frequency domain-aware SAR image generation model based on the denoising diffusion probabilistic model. The proposed generative model is capable of producing highly realistic artificial SAR image samples while converging stably. Meanwhile, our research reveals that high-frequency (HF) components of SAR images play a crucial role in the generation process, and a frequency adjustment module (FAM) based on the fast Fourier transform is implemented in our generation model to prevent interference of HF components by low-frequency components. Tests on the MSTAR dataset highlight our model's advantages in both generation quality and parameter efficiency compared to other cutting-edge image generation models. An additional ablation study also confirms the effectiveness of our proposed FAM, which reduces the Fréchet inception distance by 2.85%, confirming our hypothesis that HF components are more crucial to SAR image generation.