S³OIL: Semi-Supervised SAR-to-Optical Image Translation via Multi-Scale and Cross-Set Matching

Image-to-image translation has achieved great success, but still faces the significant challenge of limited paired data, particularly in translating Synthetic Aperture Radar (SAR) images to optical images. Furthermore, most existing semi-supervised methods place limited emphasis on leveraging the data distribution. To address those challenges, we propose a Semi-Supervised SAR-to-Optical Image Translation (S³OIL) method that achieves high-quality image generation using minimal paired data and extensive unpaired data while strategically exploiting the data distribution. To this end, we first introduce a Cross-Set Alignment Matching (CAM) mechanism to create local correspondences between the generated results of paired and unpaired data, ensuring cross-set consistency. In addition, for unpaired data, we apply weak and strong perturbations and establish intra-set Multi-Scale Matching (MSM) constraints. For paired data, intra-modal semantic consistency (ISC) is presented to ensure alignment with the ground truth. Finally, we propose local and global cross-modal semantic consistency (CSC) to boost structural identity during translation. We conduct extensive experiments on SAR-to-optical datasets and another sketch-to-anime task, demonstrating that S³OIL delivers competitive performance compared to state-of-the-art unsupervised, supervised, and semi-supervised methods, both quantitatively and qualitatively. Ablation studies further reveal that S³OIL can ensure the preservation of both semantic content and structural integrity of the generated images. Our code is available at: https://github.com/XduShi/SOIL.