Deep neural networks in single-shot ptychography

被引：14

作者：

Wengrowicz, Omri ^{[1
,2
]}

Peleg, Or ^{[1
,2
]}

Zahavy, Tom ^{[3
]}

Loevsky, Barry ^{[1
,2
]}

Cohen, Oren ^{[1
,2
]}

机构：

[1] Technion, Dept Phys, IL-32000 Haifa, Israel

[2] Technion, Solid State Inst, IL-32000 Haifa, Israel

[3] Technion, Dept EE, IL-32000 Haifa, Israel

来源：

OPTICS EXPRESS | 2020年 / 28卷 / 12期

基金：

欧盟地平线“2020”;

关键词：

LEARNING RECONSTRUCTION;

D O I：

10.1364/OE.393961

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

We develop and explore a deep learning based single-shot ptychography reconstruction method. We show that a deep neural network, trained using only experimental data and without any model of the system, leads to reconstructions of natural real-valued images with higher spatial resolution and better resistance to systematic noise than common iterative algorithms. (C) 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

引用

页码：17511 / 17520

页数：10