Generative Artificial Intelligence Meets Synthetic Aperture Radar: A survey

Synthetic aperture radar (SAR) images possess unique attributes that present challenges for both human observers and vision artificial intelligence (AI) models to interpret, owing to their electromagnetic characteristics. The interpretation of SAR images encounters various hurdles, with one of the primary obstacles being the data themselves, including issues related to both the quantity and quality of the data. The challenges can be addressed using generative AI (GenAI) technologies. GenAI is a very advanced and powerful technology in the field of AI that has gained significant attention. Its advancement has created possibilities for the creation of texts, photorealistic pictures, videos, and material in various modalities. This article aims to comprehensively investigate the intersection of GenAI and SAR. First, we illustrate the common data generation-based applications in the SAR field and compare them with computer vision tasks, analyzing their similarities, differences, and general challenges. Then, an overview of the latest GenAI models is systematically reviewed, including various basic models and their variations and targeting the general challenges. Additionally, the corresponding applications in the SAR domain are included. Specifically, we propose to summarize the physical model-based simulation approaches for SAR and analyze the hybrid modeling methods that combine the GenAI and interpretable models. The evaluation methods that have been or could be applied to SAR are also explored. Finally, potential challenges and future prospects are discussed. To our best knowledge, this survey is the first exhaustive examination of the interdiscipline of SAR and GenAI, encompassing a wide range of topics, including deep neural networks, physical models, computer vision, and SAR images.