We demonstrate digital hologram rendering by a convolutional neural network, trained with image pairs generated by wave propagation from random data. Experimental Gabor magnitude holograms are reconstructed by a U-Net trained with 50,000 image pairs.

© 2019 The Author(s)

PDF Article


You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
Login to access OSA Member Subscription