Probabilistic Diffusion Models (PDMs) have recently emerged as a very promising class of generative models, achieving high performance in natural image generation. However, their performance relative to non-natural images, like radar-based satellite data, remains largely unknown. Generating large amounts of synthetic (and especially labelled) satellite data is crucial to implement deep-learning approaches for the processing and analysis of (interferometric) satellite aperture radar data. Here, we leverage PDMs to generate several radar-based satellite image datasets. We show that PDMs succeed in generating images with complex and realistic structures, but that sampling time remains an issue. Indeed, accelerated sampling strategies, which work well on simple image datasets like MNIST, fail on our radar datasets. We provide a simple and versatile open-source https://github.com/thomaskerdreux/PDM_SAR_InSAR_generation to train, sample and evaluate PDMs using any dataset on a single GPU.

翻译：概率扩散模型（Probabilistic Diffusion Models, PDMs）近期作为一类极具前景的生成模型脱颖而出，在自然图像生成任务中取得了优异性能。然而，该类模型在非自然图像（如雷达卫星数据）上的表现仍鲜有研究。生成大量合成（尤其是有标注的）卫星数据对于采用深度学习方法处理与分析（干涉）合成孔径雷达数据至关重要。本研究利用PDMs生成了多个基于雷达的卫星图像数据集。研究结果表明，PDMs能够成功生成具有复杂且逼真结构的图像，但采样时间仍是亟待解决的问题。事实上，在MNIST等简单图像数据集上表现良好的加速采样策略，在雷达数据集上效果不佳。我们提供了一个简洁且通用的开源项目https://github.com/thomaskerdreux/PDM_SAR_InSAR_generation，支持在单个GPU上使用任意数据集进行PDMs的训练、采样与评估。