IFNet: Deep Imaging and Focusing for Handheld SAR with Millimeter-wave Signals

TL;DR

This paper introduces IFNet, a deep unfolding network that enhances handheld millimeter-wave SAR imaging by compensating for phase errors and improving image quality through a novel integration of signal models and neural networks.

Contribution

The paper presents a new deep unfolding network, IFNet, that effectively models and corrects phase errors in handheld mmWave SAR imaging, outperforming existing methods.

Findings

Achieves at least 11.89 dB PSNR improvement

Attains 64.91% SSIM enhancement

Effectively compensates for handheld phase errors

Abstract

Recent advancements have showcased the potential of handheld millimeter-wave (mmWave) imaging, which applies synthetic aperture radar (SAR) principles in portable settings. However, existing studies addressing handheld motion errors either rely on costly tracking devices or employ simplified imaging models, leading to impractical deployment or limited performance. In this paper, we present IFNet, a novel deep unfolding network that combines the strengths of signal processing models and deep neural networks to achieve robust imaging and focusing for handheld mmWave systems. We first formulate the handheld imaging model by integrating multiple priors about mmWave images and handheld phase errors. Furthermore, we transform the optimization processes into an iterative network structure for improved and efficient imaging performance. Extensive experiments demonstrate that IFNet effectively compensates for handheld phase errors and recovers high-fidelity images from severely distorted signals. In comparison with existing methods, IFNet can achieve at least 11.89 dB improvement in average peak signal-to-noise ratio (PSNR) and 64.91% improvement in average structural similarity index measure (SSIM) on a real-world dataset.