Multi-Frequency Progressive Refinement for Learned Inverse Scattering

TL;DR

This paper introduces MFISNet, a neural network that progressively refines inverse scattering reconstructions across multiple frequencies, significantly improving accuracy for complex, high-contrast inhomogeneous media.

Contribution

The paper presents a novel multi-frequency neural network architecture inspired by recursive linearization, enhancing inverse scattering imaging of complex media.

Findings

MFISNet outperforms previous methods in high-contrast scenarios

The recursive refinement approach improves stability and accuracy

Effective in reconstructing complex inhomogeneous backgrounds

Abstract

Interpreting scattered acoustic and electromagnetic wave patterns is a computational task that enables remote imaging in a number of important applications, including medical imaging, geophysical exploration, sonar and radar detection, and nondestructive testing of materials. However, accurately and stably recovering an inhomogeneous medium from far-field scattered wave measurements is a computationally difficult problem, due to the nonlinear and non-local nature of the forward scattering process. We design a neural network, called Multi-Frequency Inverse Scattering Network (MFISNet), and a training method to approximate the inverse map from far-field scattered wave measurements at multiple frequencies. We consider three variants of MFISNet, with the strongest performing variant inspired by the recursive linearization method--a commonly used technique for stably inverting scattered wavefield data--that progressively refines the estimate with higher frequency content. MFISNet outperforms past methods in regimes with high-contrast, heterogeneous large objects, and inhomogeneous unknown backgrounds.