Abstract

We use deep learning to optimize the end-to-end design of computational microscopes, jointly designing the hardware for data collection and processing software for object reconstruction. With this framework, we optimize the illumination pattern for high space-bandwidth product imaging and 3-dimensional imaging.

© 2019 The Author(s)

PDF Article
This paper was not presented at the conference

References

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
or
Login to access OSA Member Subscription