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.
In Virtual SAR we have infused images with varying level of noise, which helps in improving the accuray fo blind denoising task. The holdout set can be created using images from USC SIPI Aerials database and the the provided matlab script (preprocess_holdout.m) tested on Matlab R2019b.
The usage for research purposes is for free. If you use this dataset, please cite the following paper along with the dataset: Virtual SAR: A Synthetic Dataset for Deep Learning based Speckle Noise Reduction Algorithms
- virtual_sar_training_set.zip (1.24 GB)