Nonlocal methods are state-of-the-art in SAR despeckling, thanks to their ability to exploit image self-similarity. Given sufficient training data, however, methods based on deep learning have proven highly competitive. Therefore, to take the best of both approaches, we investigate the use of deep learning to improve nonlocal despeckling. We use plain non-iterative nonlocal means despeckling, with weights provided, for each estimation window, by a suitably trained deep CNN. Experiments on synthetic and real SAR data prove this approach to outperform conventional nonlocal methods.
Nonlocal Sar Image Despeckling by Convolutional Neural Networks / Cozzolino, Davide; Verdoliva, Luisa; Scarpa, Giuseppe; Poggi, Giovanni. - (2019), pp. 5117-5120. (Intervento presentato al convegno 39th IEEE International Geoscience and Remote Sensing Symposium) [10.1109/IGARSS.2019.8897761].
Nonlocal Sar Image Despeckling by Convolutional Neural Networks
Davide Cozzolino;Luisa Verdoliva;Giuseppe Scarpa;Giovanni Poggi
2019
Abstract
Nonlocal methods are state-of-the-art in SAR despeckling, thanks to their ability to exploit image self-similarity. Given sufficient training data, however, methods based on deep learning have proven highly competitive. Therefore, to take the best of both approaches, we investigate the use of deep learning to improve nonlocal despeckling. We use plain non-iterative nonlocal means despeckling, with weights provided, for each estimation window, by a suitably trained deep CNN. Experiments on synthetic and real SAR data prove this approach to outperform conventional nonlocal methods.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
