Reference-Free Despeckling of Synthetic-Aperture Radar Images Using a Deep Convolutional Network
Timothy Davis, Vijal Jain, Andreas Ley, Olivier D’Hondt, Sébastien Valade, Olaf Hellwich · 2020
This work proposes a deep learning based method to de-speckle SAR images that does not require noise-free reference data. Instead, our method exploits the redundancy between images of the same area at different times to train a residual convolutional neural network in a regression framework to predict speckle-free images. Moreover, thanks to end-to-end training of the network, our approach does not require explicit parameter tuning. Experiments show the relevance of our approach on Sentinel 1 images acquired over volcanic areas. The method is shown to compete well with well-known approaches such as the Lee filter and the more recent SAR-BM3D filter.