Physics-enhanced neural network for phase retrieval from two diffraction patterns

In this work, we propose a physics-enhanced two-to-one Y-neural network (two inputs and one output) for phase retrieval of complex wavefronts from two diffraction patterns. The learnable parameters of the Y-net are optimized by minimizing a hybrid loss function, which evaluates the root-mean-square...

Full description

Saved in:
Bibliographic Details
Published inOptics express Vol. 30; no. 18; pp. 32680 - 32692
Main Authors Li, Rujia, Pedrini, Giancarlo, Huang, Zhengzhong, Reichelt, Stephan, Cao, Liangcai
Format Journal Article
LanguageEnglish
Published 29.08.2022
Online AccessGet full text

Cover

More Information
Summary:In this work, we propose a physics-enhanced two-to-one Y-neural network (two inputs and one output) for phase retrieval of complex wavefronts from two diffraction patterns. The learnable parameters of the Y-net are optimized by minimizing a hybrid loss function, which evaluates the root-mean-square error and normalized Pearson correlated coefficient on the two diffraction planes. An angular spectrum method network is designed for self-supervised training on the Y-net. Amplitudes and phases of wavefronts diffracted by a USAF-1951 resolution target, a phase grating of 200 lp/mm, and a skeletal muscle cell were retrieved using a Y-net with 100 learning iterations. Fast reconstructions could be realized without constraints or a priori knowledge of the samples.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1094-4087
1094-4087
DOI:10.1364/OE.469080