Presenter: Andrea Bordone Molini
Monday, July 6th, 2020 16:30
Location: Microsoft Teams – click here to join
Information extraction from synthetic aperture radar (SAR) images is heavily impaired by speckle noise, hence despeckling is a crucial preliminary step in scene analysis algorithms. The recent success of deep learning promises a new generation of despeckling techniques that could outperform classical model- based methods. However, current deep learning approaches to despeckling require supervision for training and clean SAR images are impossible to obtain. In the literature, this issue is tackled by resorting to either synthetically speckled optical images, which exhibit different properties with respect to true SAR data, or multi-temporal SAR images, which are difficult to acquire or fuse accurately. In this paper, inspired by recent works on blind-spot denoising networks, we propose a self-supervised Bayesian despeckling method. The proposed method is trained employing only noisy SAR images and can therefore learn features of real SAR images rather than synthetic data.
Andrea Bordone Molini received the M.Sc. degree in computer networks engineering from the Politecnico di Torino, Turin, Italy, and the M.Sc. degree in communications systems security from the Télécom ParisTech, Paris, France, as a part of a double degree program in 2016. He is currently pursuing the Ph.D. degree with the SmartData@PoliTo Research Center. His current research interest includes deep learning applied to image processing in particular in the fields of super-resolution and denoising.