Deep Denoising Prior-Based Spectral Estimation for Phaseless Synthetic Aperture Radar

TL;DR

This paper introduces a deep learning-based spectral estimation method for phaseless SAR imaging, enhancing initialization and reconstruction quality by integrating deep denoisers into an iterative framework, verified through synthetic data.

Contribution

It presents a novel deep denoising prior-based spectral estimation technique for phaseless SAR that extends traditional spectral methods with deep learning, improving imaging performance.

Findings

Effective spectral estimation with deep denoisers

Improved SAR image reconstruction quality

Feasibility demonstrated on synthetic data

Abstract

Incoherent processing for synthetic aperture radar (SAR) is a promising approach that enables low implementation costs, simplified hardware designs and operations in high frequency spectrum compared to the conventional imaging methods using coherent processing. Existing non-convex phaseless imaging algorithms offer recovery guarantees over limited range of forward models. In recent years, several deep learning (DL) based techniques have been introduced with the goal of extending applicability of phaseless imaging techniques to wave-based imaging modalities by addressing fundamental challenges, such as, lack of redundancy, non-uniqueness issues encountered commonly with inverse scattering models. In this paper, we introduce a DL-based phaseless SAR imaging approach that is designed under the premise that the spectral estimation technique, widely used for initializing non-convex phase retrieval algorithms, has significance far beyond generating good initial points. We extend the iterative power method for spectral estimation by using deep denoisers at each iteration, and subsequently design a deep imaging network within the plug-and-play framework. Finally, we verify the feasibility of our approach using synthetic SAR measurements.