InSAR-MONet: Interferometric SAR Phase Denoising Using a Multiobjective Neural Network

Interferometric synthetic aperture radar (SAR) is an effective and widely adopted tool for Earth observation. Based on interferograms, it is possible to infer several information about the observed areas. Two main problems affecting the interferogram can limit its application: phase noise and phase wrapping. In this article, the attention is focused on the first issue. Several algorithms have been developed for interferogram restoration. Given the widespread of deep learning (DL) in the framework of image processing, DL-based algorithms have been proposed for interferogram denoising. Most of the efforts have been devoted to designing specific network architectures or training datasets, rather than to the definition of a specific cost function, well suited for the problem under investigation. The aim of this article is to define a new multiobjective cost function, specifically thought for the interferograms restoration problem: the idea is to provide a cost function able to take into account multiple aspects of the data under investigation (i.e., multiobjective). The cost function is implemented within a convolutional neural network and a specific realistic training dataset is built, to account for the main characteristics of real interferograms. The final outcome of this article is the proposal of a new robust and accurate interferometric phase denoising algorithm (namely, InSAR-MONet), able to remove undesired noise and, at the same time, able to preserve important phase details. The assessment of the method is conducted on simulated and real datasets, comparing quantitatively and qualitatively InSAR-MONet with the state-of-the-art interferometric denoising algorithms.