Abstract

Learning-based computer-generated holography (CGH) provides a rapid hologram generation approach for holographic displays. Supervised training requires a large-scale dataset with target images and corresponding holograms. We propose an autoencoder-based neural network (holoencoder) for phase-only hologram generation. Physical diffraction propagation was incorporated into the autoencoder’s decoding part. The holoencoder can automatically learn the latent encodings of phase-only holograms in an unsupervised manner. The proposed holoencoder was able to generate high-fidelity 4K resolution holograms in 0.15 s. The reconstruction results validate the good generalizability of the holoencoder, and the experiments show fewer speckles in the reconstructed image compared with the existing CGH algorithms.

© 2021 Optical Society of America

Diffraction model-informed neural network for unsupervised layer-based computer-generated holography

Xinghua Shui, Huadong Zheng, Xinxing Xia, Furong Yang, Weisen Wang, and Yingjie Yu
Opt. Express 30(25) 44814-44826 (2022)

Asymmetrical neural network for real-time and high-quality computer-generated holography

Guangwei Yu, Jun Wang, Huan Yang, Zicheng Guo, and Yang Wu
Opt. Lett. 48(20) 5351-5354 (2023)

Fourier-inspired neural module for real-time and high-fidelity computer-generated holography

Zhenxing Dong, Chao Xu, Yuye Ling, Yan Li, and Yikai Su
Opt. Lett. 48(3) 759-762 (2023)

DCPNet: a dual-channel parallel deep neural network for high quality computer-generated holography

Qingwei Liu, Jing Chen, Bingsen Qiu, Yongtian Wang, and Juan Liu
Opt. Express 31(22) 35908-35921 (2023)

Computer holography using deep neural network with Fourier basis

Runze Zhu, Lizhi Chen, and Hao Zhang
Opt. Lett. 48(9) 2333-2336 (2023)