Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey

Abstract

SAR images possess unique attributes that present challenges for both human observers and vision 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 itself, which includes issues related to both the quantity and quality of the data. The challenges can be addressed using generative AI technologies. Generative AI, often known as GenAI, is a very advanced and powerful technology in the field of artificial intelligence that has gained significant attention. The advancement has created possibilities for the creation of texts, photorealistic pictures, videos, and material in various modalities. This paper aims to comprehensively investigate the intersection of GenAI and SAR. First, we illustrate the common data generation-based applications in SAR field and compare them with computer vision tasks, analyzing the similarity, difference, and general challenges of them. Then, an overview of the latest GenAI models is systematically reviewed, including various basic models and their variations targeting the general challenges. Additionally, the corresponding applications in SAR domain are also 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, the 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. The resources of this survey are open-source at \url{https://github.com/XAI4SAR/GenAIxSAR}.

References in corpus (22)

• Conditional Generative Adversarial Nets
• Generative Adversarial Networks
• LLaMA: Open and Efficient Foundation Language Models
• Diffusion Models Beat GANs on Image Synthesis
• Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
• Temporal Ensembling for Semi-Supervised Learning
• Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
• Alias-Free Generative Adversarial Networks
• Classifier-Free Diffusion Guidance
• LaMDA: Language Models for Dialog Applications
• Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis
• Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
• SAR Target Image Generation Method Using Azimuth-Controllable Generative Adversarial Network
• The QXS-SAROPT Dataset for Deep Learning in SAR-Optical Data Fusion
• DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data
• Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks
• SatDM: Synthesizing Realistic Satellite Image with Semantic Layout Conditioning using Diffusion Models
• SDDPM: Speckle Denoising Diffusion Probabilistic Models
• DiffCR: A Fast Conditional Diffusion Framework for Cloud Removal from Optical Satellite Images
• TSGAN: An Optical-to-SAR Dual Conditional GAN for Optical based SAR Temporal Shifting
• Reinforcement Learning for SAR View Angle Inversion with Differentiable SAR Renderer
• X-Fake: Juggling Utility Evaluation and Explanation of Simulated SAR Images