SAR2SAR: a semi-supervised despeckling algorithm for SAR images
This addresses speckle reduction in SAR images for remote sensing applications, offering an incremental improvement with a novel adaptation of existing methods.
The paper tackles SAR image despeckling by proposing SAR2SAR, a semi-supervised deep learning algorithm that uses multi-temporal time series and the noise2noise framework to restore images from noisy acquisitions, achieving competitive results compared to state-of-the-art filters in synthetic and real image tests.
Speckle reduction is a key step in many remote sensing applications. By strongly affecting synthetic aperture radar (SAR) images, it makes them difficult to analyse. Due to the difficulty to model the spatial correlation of speckle, a deep learning algorithm with self-supervision is proposed in this paper: SAR2SAR. Multi-temporal time series are leveraged and the neural network learns to restore SAR images by only looking at noisy acquisitions. To this purpose, the recently proposed noise2noise framework has been employed. The strategy to adapt it to SAR despeckling is presented, based on a compensation of temporal changes and a loss function adapted to the statistics of speckle. A study with synthetic speckle noise is presented to compare the performances of the proposed method with other state-of-the-art filters. Then, results on real images are discussed, to show the potential of the proposed algorithm. The code is made available to allow testing and reproducible research in this field.