Seeing through a Black Box: Toward High-Quality Terahertz TomographicImaging via Multi-Scale Spatio-Spectral Image Fusion
This work addresses image quality issues in terahertz imaging for non-invasive inspection, representing an incremental improvement over existing methods.
The paper tackles the problem of blur and distortion in terahertz tomographic imaging due to water absorption and low noise tolerance, proposing SARNet which fuses multi-spectral features to achieve high-quality restoration, with experimental results showing effectiveness in 3D reconstruction.
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