We propose to use autoencoder and a two-stage training strategy for image reconstruction in multimode fiber imaging system. Compared with the conventional method of U-net, this approach achieves higher reconstruction accuracy and faster convergence speed.

© 2020 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