Phase retrieval using single-instance deep generative prior

Kshitij Tayal, Raunak Manekar, Zhong Zhuang, David Yang, Vipin Kumar, Felix Hofmann, Ju Sun

Research output: Contribution to journalConference articlepeer-review

Abstract

Several deep learning methods for phase retrieval exist, but most of them fail on realistic data without precise support information. We propose a novel method based on single-instance deep generative prior that works well on complex-valued crystal data.

Original languageEnglish (US)
Article numberJW2A.37
JournalOptics InfoBase Conference Papers
StatePublished - 2021
EventApplied Industrial Spectroscopy, AIS 2021 - Part of Optical Sensors and Sensing Congress 2021 - Virtual, Online, United States
Duration: Jul 19 2021Jul 23 2021

Bibliographical note

Publisher Copyright:
© OSA 2021, © 2021 The Author(s)

Fingerprint

Dive into the research topics of 'Phase retrieval using single-instance deep generative prior'. Together they form a unique fingerprint.

Cite this