Logo image
Multi-Band Spectral Fusion Terahertz Deep Learning Computed Tomography
Conference paper

Multi-Band Spectral Fusion Terahertz Deep Learning Computed Tomography

Ta-Hsuan Chao, Weng-Tai Su, Chia-Wen Lin and Shang-Hua Yang
International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz, Vol.2021-August
2021

Abstract

Energy Engineering and Power Technology Electrical and Electronic Engineering
We present a novel method to visualize 3D object details through a multi-band spectral fusion deep learning approach. This method, multi-dominant-band spatio-spectral fusion network (MS-Unet), incorporates rich information from multi-frequency band spectral data. The reconstructed terahertz tomographic images significantly outperform conventional methods, enhancing 8.97 dB in PSNR, boosting SSIM from 0.05 to 0.70, and improving LPIPS from 0.36 to 0.18.

Metrics

1 Record Views

Details

Logo image