Quantum-weighted autoencoder for compression computer-generated holograms

We propose a quantum-weighted autoencoder network for compression computer-generated holograms. And the quantum-weighted autoencoder consists of embedding, entanglement, and measurement layers. Experimental results show that the image quality of computer-generated holograms reconstructed by this quantum network is generally better than that of traditional autoencoders. The training stability of the network is better than that of a traditional autoencoder, and the convergence of the network is faster.