Unsupervised SAR Image Super-Resolution With Despeckling via Region-Specific Diffusion Models

Super-resolution (SR) and despeckling for Synthetic Aperture Radar (SAR) images are critical tasks. However, these tasks are challenging due to speckle noise and low resolution. Speckle noise, caused by the coherent imaging mechanism, severely degrades image quality, while low resolution limits the preservation of structural details and textures. Existing methods often fail to effectively balance noise suppression and texture reconstruction, especially when addressing both tasks simultaneously. To tackle these challenges, this paper proposes an unsupervised framework that combines Training for Region-Specific Diffusion Model (RSDM) and Latent Space Integration for Reconstruction (LSIR). RSDM uses Low-Rank Adaptation (LoRA) to train diffusion models tailored for homogeneous and inhomogeneous regions, enabling it to capture statistical uniformity and low-frequency features in homogeneous regions, while focusing on structural complexity and high-frequency details in inhomogeneous regions. LSIR integrates these region-specific models through Bézier interpolation for latent noise and linear interpolation for functional integration, allowing simultaneous high-quality despeckling and super-resolution. Experiments conducted on multiple SAR datasets confirm the effectiveness of the proposed framework. The results demonstrate significant improvements over state-of-the-art methods in structural detail preservation, noise reduction, and overall visual quality.