Seeing through a Black Box: Toward High-Quality Terahertz TomographicImaging via Multi-Scale Spatio-Spectral Image Fusion

TL;DR

This paper introduces SARNet, a novel deep learning model that fuses multi-spectral THz images to improve the quality of 3D tomographic reconstructions, overcoming diffraction limits and image distortions.

Contribution

The paper presents SARNet, a new subspace-and-attention-guided network that effectively restores THz images by leveraging multi-scale spatio-spectral feature fusion.

Findings

SARNet significantly improves THz image quality.

Enhanced 3D tomographic reconstruction accuracy.

Effective handling of water absorption and noise distortions.

Abstract

Terahertz (THz) imaging has recently attracted significant attention thanks to its non-invasive, non-destructive, non-ionizing, material-classification, and ultra-fast nature for object exploration and inspection. However, its strong water absorption nature and low noise tolerance lead to undesired blurs and distortions of reconstructed THz images. The performances of existing restoration methods are highly constrained by the diffraction-limited THz signals. To address the problem, we propose a novel Subspace-and-Attention-guided Restoration Network (SARNet) that fuses multi-spectral features of a THz image for effective restoration. To this end, SARNet uses multi-scale branches to extract spatio-spectral features of amplitude and phase which are then fused via shared subspace projection and attention guidance. Here, we experimentally construct ultra-fast THz time-domain spectroscopy system covering a broad frequency range from 0.1 THz to 4 THz for building up temporal/spectral/spatial/phase/material THz database of hidden 3D objects. Complementary to a quantitative evaluation, we demonstrate the effectiveness of our SARNet model on 3D THz tomographic reconstruction