SAR Image Despeckling Using a Convolutional Neural Network
This addresses the difficulty in processing and interpreting SAR images for remote sensing and imaging applications, but appears incremental as it builds on existing CNN approaches.
The paper tackles the problem of speckle noise in Synthetic Aperture Radar (SAR) images by proposing ID-CNN, a deep learning-based method that achieves significant improvements over state-of-the-art speckle reduction techniques.
Synthetic Aperture Radar (SAR) images are often contaminated by a multiplicative noise known as speckle. Speckle makes the processing and interpretation of SAR images difficult. We propose a deep learning-based approach called, Image Despeckling Convolutional Neural Network (ID-CNN), for automatically removing speckle from the input noisy images. In particular, ID-CNN uses a set of convolutional layers along with batch normalization and rectified linear unit (ReLU) activation function and a component-wise division residual layer to estimate speckle and it is trained in an end-to-end fashion using a combination of Euclidean loss and Total Variation (TV) loss. Extensive experiments on synthetic and real SAR images show that the proposed method achieves significant improvements over the state-of-the-art speckle reduction methods.