Abstract
The existing iterative and data-driven methods fail to solve phase retrieval due to the intrinsic problem symmetries. We propose two end-to-end learning methods that break the barrier and work in a new regime.
Original language | English (US) |
---|---|
Article number | CTh4A.4 |
Journal | Optics InfoBase Conference Papers |
State | Published - 2021 |
Event | Computational Optical Sensing and Imaging, COSI 2021 - Part of OSA Imaging and Applied Optics Congress 2021 - Virtual, Online, United States Duration: Jul 19 2021 → Jul 23 2021 |
Bibliographical note
Publisher Copyright:© OSA 2021, © 2021 The Author(s)