HyperLISTA-ABT: An Ultra-light Unfolded Network for Accurate Multi-component Differential Tomographic SAR Inversion

TL;DR

HyperLISTA-ABT is an ultra-light neural network designed for efficient and accurate 4D differential TomoSAR inversion, overcoming high-dimensional weight challenges with an analytical weight determination and adaptive thresholding.

Contribution

The paper introduces HyperLISTA-ABT, a novel ultra-light deep learning model for 4D TomoSAR that reduces complexity and enhances efficiency through analytical weights and adaptive thresholding.

Findings

HyperLISTA-ABT achieves superior computational efficiency.

It maintains high reconstruction quality comparable to state-of-the-art methods.

Real data experiments demonstrate fast, high-quality 4D point cloud reconstruction.

Abstract

Deep neural networks based on unrolled iterative algorithms have achieved remarkable success in sparse reconstruction applications, such as synthetic aperture radar (SAR) tomographic inversion (TomoSAR). However, the currently available deep learning-based TomoSAR algorithms are limited to three-dimensional (3D) reconstruction. The extension of deep learning-based algorithms to four-dimensional (4D) imaging, i.e., differential TomoSAR (D-TomoSAR) applications, is impeded mainly due to the high-dimensional weight matrices required by the network designed for D-TomoSAR inversion, which typically contain millions of freely trainable parameters. Learning such huge number of weights requires an enormous number of training samples, resulting in a large memory burden and excessive time consumption. To tackle this issue, we propose an efficient and accurate algorithm called HyperLISTA-ABT. The weights in HyperLISTA-ABT are determined in an analytical way according to a minimum coherence criterion, trimming the model down to an ultra-light one with only three hyperparameters. Additionally, HyperLISTA-ABT improves the global thresholding by utilizing an adaptive blockwise thresholding scheme, which applies block-coordinate techniques and conducts thresholding in local blocks, so that weak expressions and local features can be retained in the shrinkage step layer by layer. Simulations were performed and demonstrated the effectiveness of our approach, showing that HyperLISTA-ABT achieves superior computational efficiency and with no significant performance degradation compared to state-of-the-art methods. Real data experiments showed that a high-quality 4D point cloud could be reconstructed over a large area by the proposed HyperLISTA-ABT with affordable computational resources and in a fast time.