Sim2Real SAR Image Restoration: Metadata-Driven Models for Joint Despeckling and Sidelobes Reduction

TL;DR

This paper introduces a unified neural network framework for joint despeckling and sidelobes reduction in SAR images, leveraging simulated data and metadata to enhance real-world restoration performance.

Contribution

The paper presents a novel joint restoration approach using metadata-driven neural networks trained on simulated SAR data, enabling effective Sim2Real transfer.

Findings

Effective joint despeckling and sidelobes reduction demonstrated

Metadata incorporation improves restoration quality

Successful transfer from simulated to real SAR images

Abstract

Synthetic aperture radar (SAR) provides valuable information about the Earth's surface under all weather and illumination conditions. However, the inherent phenomenon of speckle and the presence of sidelobes around bright targets pose challenges for accurate interpretation of SAR imagery. Most existing SAR image restoration methods address despeckling and sidelobes reduction as separate tasks. In this paper, we propose a unified framework that jointly performs both tasks using neural networks (NNs) trained on a realistic SAR simulated dataset generated with MOCEM. Inference can then be performed on real SAR images, demonstrating effective simulation to real (Sim2Real) transferability. Additionally, we incorporate acquisition metadata as auxiliary input to the NNs, demonstrating improved restoration performance.