Learning to synthesize: robust phase retrieval at low photon counts

The quality of inverse problem solutions obtained through deep learning is limited by the nature of the priors learned from examples presented during the training phase. Particularly in the case of quantitative phase retrieval, spatial frequencies that are underrepresented in the training database,...

Full description

Bibliographic Details
Main Authors: Deng, Mo (Author), Li, Shuai (Author), Goy, Alexandre (Author), Kang, Iksung (Author), Barbastathis, George (Author)
Other Authors: Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor), Massachusetts Institute of Technology. Department of Mechanical Engineering (Contributor), Singapore-MIT Alliance in Research and Technology (SMART) (Contributor)
Format: Article
Language:English
Published: Springer Science and Business Media LLC, 2020-06-30T22:04:43Z.
Subjects:
Online Access:Get fulltext