TomoSAR-ALISTA: Efficient TomoSAR Imaging via Deep Unfolded Network

TL;DR

This paper introduces TomoSAR-ALISTA, a deep unfolded network that improves 3D SAR imaging by learning ISTA parameters, reducing computational complexity and enhancing reconstruction quality without extensive parameter tuning.

Contribution

The paper proposes a novel deep unfolded network, ALISTA, for TomoSAR imaging that learns ISTA parameters from data, eliminating manual tuning and improving efficiency.

Findings

ALISTA achieves better 3D reconstruction quality.

The method reduces training complexity by using traditional CS algorithms as labels.

Experimental results validate the effectiveness of ALISTA in TomoSAR imaging.

Abstract

Synthetic aperture radar (SAR) tomography (TomoSAR) has attracted remarkable interest for its ability in achieving three-dimensional reconstruction along the elevation direction from multiple observations. In recent years, compressed sensing (CS) technique has been introduced into TomoSAR considering for its super-resolution ability with limited samples. Whereas, the CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity and complex parameter fine-tuning. Among the different CS algorithms, iterative soft-thresholding algorithm (ISTA) is widely used as a robust reconstruction approach, however, the parameters in the ISTA algorithm are manually chosen, which usually requires a time-consuming fine-tuning process to achieve the best performance. Aiming at efficient TomoSAR imaging, a novel sparse unfolding network named analytic learned ISTA (ALISTA) is proposed towards the TomoSAR imaging problem in this paper, and the key parameters of ISTA are learned from training data via deep learning to avoid complex parameter fine-tuning and significantly relieves the training burden. In addition, experiments verify that it is feasible to use traditional CS algorithms as training labels, which provides a tangible supervised training method to achieve better 3D reconstruction performance even in the absence of labeled data in real applications.