2 papers
physics.optics2024
Reconstruction of partially occluded objects with a physics-driven self-training neural network
Mingjun Xiang, Kai Zhou, Hui Yuan +1
This study proposes a novel approach utilizing a physics-informed deep learning (DL) algorithm to reconstruct occluded objects in a terahertz (THz) holographic system. Taking the a…
physics.optics2024
Hybrid Multi-Head Physics-informed Neural Network for Depth Estimation in Terahertz Imaging
Mingjun Xiang, Hui Yuan, Kai Zhou +1
Terahertz (THz) imaging is one of the hotspots in the field of optics, where the depth information retrieval is a key factor to restore the three-dimensional appearance of objects.…