Virtual SAR: A Synthetic Dataset for Deep Learning based Speckle Noise Reduction Algorithms

Synthetic Aperture Radar (SAR) images can be extensively informative owing to their resolution and availability. However, the removal of speckle-noise from these requires several pre-processing steps. In recent years, deep learning-based techniques have brought significant improvement in the domain of denoising and image restoration. However, further research has been hampered by the lack of availability of data suitable for training deep neural network-based systems. With this paper, we propose a standard synthetic data set for the training of speckle reduction algorithms. The design of image processing techniques for synthetic aperture radar applications requires testing and validation on real and synthetic images. The Virtual SAR dataset provides synthetic data to support the design and analysis of algorithms to deal with SAR data.

合成孔径雷达（Synthetic Aperture Radar，SAR）图像凭借其分辨率与可获取性，具备丰富的信息价值。然而，从中去除斑点噪声需要开展多步预处理操作。近年来，基于深度学习的技术在降噪与图像复原领域取得了显著进展。然而，适配基于深度神经网络系统训练的可用数据匮乏，掣肘了相关研究的进一步推进。本文提出了一款用于斑点噪声抑制算法训练的标准合成数据集。合成孔径雷达应用中的图像处理技术研发，需要依托真实与合成图像开展测试与验证工作。本虚拟SAR数据集提供合成数据，用于支撑面向SAR数据的算法设计与分析工作。