Purely Speckled Intensity Images Need for SAR Despeckling with SDS-SAR

TL;DR

This paper introduces SDS-SAR, a self-supervised despeckling method for SAR images that does not require speckle-free references, achieving comparable or superior results to supervised methods on real data.

Contribution

The paper presents a novel self-supervised SAR despeckling strategy that operates solely on speckled intensity images, eliminating the need for speckle-free training data.

Findings

Performs on par with supervised methods on synthetic data

Outperforms supervised methods on real SAR data

Balances speckle suppression with texture preservation

Abstract

Speckle noise is generated along with the SAR imaging mechanism and degrades the quality of SAR images, leading to difficult interpretation. Hence, despeckling is an indispensable step in SAR pre-processing. Fortunately, supervised learning (SL) has proven to be a progressive method for SAR image despeckling. SL methods necessitate the availability of both original SAR images and their speckle-free counterparts during training, whilst speckle-free SAR images do not exist in the real world. Even though there are several substitutes for speckle-free images, the domain gap leads to poor performance and adaptability. Self-supervision provides an approach to training without clean reference. However, most self-supervised methods impose high demands on speckle modeling or specific data, limiting their practicality in real-world applications. To address these challenges, we propose a Self-supervised Despeckling Strategy for SAR images (SDS-SAR) that relies solely on speckled intensity data for training. Firstly, the theoretical feasibility of SAR image despeckling without speckle-free images is established. A self-supervised despeckling criteria suitable for all SAR images is proposed. Subsequently, a Random-Aware sub-SAMpler with Projection correLation Estimation (RA-SAMPLE) is put forth. Mutually independent training pairs can be derived from actual SAR intensity images. Furthermore, a multi-feature loss function is introduced, consisting of a despeckling term, a regularization term, and a perception term. The performance of speckle suppression and texture preservation is well-balanced. Experiments reveal that the proposed method performs on par with supervised approaches on synthetic data and outperforms them on actual data.