Holographic 3D particle imaging with model-based network

Ni Chen, Congli Wang, Wolfgang Heidrich
IEEE Transactions on Computational Imaging, pp. 288-296, 2021



Schematic diagram of the MB-HoloNet



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.

Resources

Paper [Chen2021TCI.pdf (4.33 MB)] 
Code [Github] 
Other Links [Github Project Page]