Unsupervised layer-based computer-generated holography using Diffraction model-informed neural network

A neural network based on a Diffraction Model for layer-based unsupervised computer-generated holography

The learning-based computer generated holography (CGH), which enables real-time holographic display, has shown great promise. A large dataset of target images and their corresponding holograms is required for supervised CGH. We propose a neural network framework (self holo) based on diffraction models for 3D phase only holograms. The neural network can be trained unsupervised without a labeled data set, as the angular spectra propagation is incorporated. The complexity of the self hologram is independent of the depth layers because it uses the different representations of 3D objects and reconstructs the hologram randomly to one of them. Self-holo uses depth and amplitude maps as input to create a 3D or 2D hologram. We show 3D reconstructions that have a good 3D appearance and demonstrate the generalizability and applicability of self-holo to numerical and optical experiments.