Generative adversarial neural network for 3D-hologram reconstruction

Abstract

Neural-network-based reconstruction of digital holograms can improve the speed and the quality of micro- and macro-object images, as well as reduce the noise and suppress the twin image and the zero-order. Usually, such methods aim to reconstruct the 2D object image or amplitude and phase distribution. In this paper, we investigated the feasibility of using a generative adversarial neural network to reconstruct 3D-scenes consisting of a set of cross-sections. The method was tested on computer-generated and optically-registered digital inline holograms. It enabled the reconstruction of all layers of a scene from each hologram. The reconstruction quality is improved 1.8 times when compared to the U-Net architecture on the normalized standard deviation value.