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
Full Article | PDF ArticleMore Like This
Xinghua Shui, Huadong Zheng, Xinxing Xia, Furong Yang, Weisen Wang, and Yingjie Yu
Opt. Express 30(25) 44814-44826 (2022)
Guangwei Yu, Jun Wang, Huan Yang, Zicheng Guo, and Yang Wu
Opt. Lett. 48(20) 5351-5354 (2023)
Zhenxing Dong, Chao Xu, Yuye Ling, Yan Li, and Yikai Su
Opt. Lett. 48(3) 759-762 (2023)