Just Project! Multi-Channel Despeckling, the Easy Way

TL;DR

This paper presents MuChaPro, a versatile framework for multi-channel SAR despeckling that leverages existing single-channel methods and self-supervised learning to improve performance in polarimetric and interferometric applications.

Contribution

MuChaPro introduces a simple, effective approach to multi-channel SAR despeckling by generating and restoring single-channel projections, enabling sensor-specific self-supervised training.

Findings

Effective in polarimetric and interferometric SAR imaging

Compatible with existing single-channel despeckling methods

Enables sensor-specific self-supervised learning

Abstract

Reducing speckle fluctuations in multi-channel SAR images is essential in many applications of SAR imaging such as polarimetric classification or interferometric height estimation. While single-channel despeckling has widely benefited from the application of deep learning techniques, extensions to multi-channel SAR images are much more challenging. This paper introduces MuChaPro, a generic framework that exploits existing single-channel despeckling methods. The key idea is to generate numerous single-channel projections, restore these projections, and recombine them into the final multi-channel estimate. This simple approach is shown to be effective in polarimetric and/or interferometric modalities. A special appeal of MuChaPro is the possibility to apply a self-supervised training strategy to learn sensor-specific networks for single-channel despeckling.