VBIM-Net: Variational Born Iterative Network for Inverse Scattering Problems

TL;DR

VBIM-Net introduces a deep learning framework that combines variational iterative methods with neural networks to improve the accuracy and stability of full-wave inverse scattering problem solutions, outperforming existing methods.

Contribution

The paper presents a novel neural network architecture, VBIM-Net, that integrates analytical contrast updates with deep learning for better inversion quality in ISPs.

Findings

High-quality inversion results on synthetic data

Robust performance on experimental data

Enhanced stability through noise-augmented training

Abstract

Recently, studies have shown the potential of integrating field-type iterative methods with deep learning (DL) techniques in solving inverse scattering problems (ISPs). In this article, we propose a novel Variational Born Iterative Network, namely, VBIM-Net, to solve the full-wave ISPs with significantly improved structural rationality and inversion quality. The proposed VBIM-Net emulates the alternating updates of the total electric field and the contrast in the variational Born iterative method (VBIM) by multiple layers of subnetworks. We embed the analytical calculation of the contrast variation into each subnetwork, converting the scattered field residual into an approximate contrast variation and then enhancing it by a U-Net, thus avoiding the requirement of matched measurement dimension and grid resolution as in existing approaches. The total field and contrast of each layer's output is supervised in the loss function of VBIM-Net, imposing soft physical constraints on the variables in the subnetworks, which benefits the model's performance. In addition, we design a training scheme with extra noise to enhance the model's stability. Extensive numerical results on synthetic and experimental data both verify the inversion quality, generalization ability, and robustness of the proposed VBIM-Net. This work may provide some new inspiration for the design of efficient field-type DL schemes.