Model-based Deep 3D holographic imaging

IEEE Transaction on Computational Imaging, 2021
Abstract
Gabor holography is a simple and effective approach for 3D imaging. However, it suffers from a DC term, twin-image entanglement, and defocus noise. The conventional approach for solving this problem is either using an off-axis setup, or compressive holography. The former sacrifices simplicity, and the latter is computationally demanding and time consuming. To cope with this problem, we propose a model-based holographic network (MB-HoloNet) for 3D particle imaging. The free-space point spread function, which is essential for hologram reconstruction, is used as a prior in the MB-HoloNet. All parameters are learned end-to-end. The physical prior makes the network efficient and stable for both localization and 3D particle size reconstructions.

Framework
framework
Fig. 1: Schematic diagram of the MB-HoloNet.
Some results
framework framework framework\ framework
framework framework framework framework
Fig. 2: Sample holograms and the corresponding reconstructions.
Downloads
The manuscript link pdf manuscript | Github project link dataset
Bibtex 
@article{Chen2020TCI,
title      = {Holographic {3D} particle imaging with model-based network},
author     = {Ni Chen and Congli Wang and Wolfgang Heidrich*},
correspond = {Wolfgang Heidrich},
journal    = {IEEE Transaction on Computational Imaging},
volume     = {7},
year       = {2021},
month      = {March},
doi        = {10.1109/TCI.2021.3063870},
url        = {http://hdl.handle.net/10754/666339},
}