RLI-DM: Robust Layout-Based Iterative Diffusion Model for SAR-to-RGB Image Translation

Synthetic aperture radar (SAR)-to-RGB translation, which transforms SAR images into visually interpretable RGB counterparts, is critical for enhancing applications in visual analysis, deep learning, and multisource data fusion. However, existing methods often fail to preserve both global structural integrity and fine-grained local textures. This deficiency stems from weak feature extraction and the lack of a robust layout framework, leading to outputs with information loss, geometric distortions, and unnatural textures. To overcome these limitations, we propose the robust layout-based iterative diffusion model (RLI-DM), a novel three-stage framework for high-fidelity translation. The framework begins with an optical reconstruction module that employs a conditional diffusion model (DM) to ensure precise spectral mapping. At its core, the geometric robustness module (GRM) leverages a Brownian bridge model that we train to derive a noise-resilient layout, overcoming the limitations of conventional edge detection and significantly enhancing global structural fidelity. Finally, this robust layout guides a customized multilevel refinement module (CMRM) to iteratively reconstruct local textures, ensuring structural clarity and cross-feature consistency. Extensive experiments on multiple benchmark datasets demonstrate that RLI-DM achieves state-of-the-art performance, significantly outperforming existing methods in both structural integrity and perceptual quality.