SAR2SAR: a semi-supervised despeckling algorithm for SAR images

TL;DR

SAR2SAR introduces a semi-supervised deep learning method leveraging multi-temporal SAR data and the noise2noise framework to effectively reduce speckle noise without requiring clean images, improving analysis of SAR images.

Contribution

The paper presents a novel self-supervised despeckling algorithm for SAR images that adapts the noise2noise framework to handle speckle noise using temporal information and specialized loss functions.

Findings

Outperforms state-of-the-art despeckling filters on synthetic data

Effectively reduces speckle noise in real SAR images

Code availability promotes reproducibility and further research

Abstract

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.