Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

PhaseGAN : a deep-learning phase-retrieval approach for unpaired datasets

Zhang, Yuhe LU ; Noack, Mike Andreas ; Vagovic, Patrik ; Fezzaa, Kamel ; Garcia-Moreno, Francisco ; Ritschel, Tobias and Villanueva-Perez, Pablo LU orcid (2021) In Optics Express 29(13). p.19593-19604
Abstract

Phase retrieval approaches based on deep learning (DL) provide a framework to obtain phase information from an intensity hologram or diffraction pattern in a robust manner and in real-time. However, current DL architectures applied to the phase problem rely on i) paired datasets, i. e., they are only applicable when a satisfactory solution of the phase problem has been found, and ii) the fact that most of them ignore the physics of the imaging process. Here, we present PhaseGAN, a new DL approach based on Generative Adversarial Networks, which allows the use of unpaired datasets and includes the physics of image formation. The performance of our approach is enhanced by including the image formation physics and a novel Fourier loss... (More)

Phase retrieval approaches based on deep learning (DL) provide a framework to obtain phase information from an intensity hologram or diffraction pattern in a robust manner and in real-time. However, current DL architectures applied to the phase problem rely on i) paired datasets, i. e., they are only applicable when a satisfactory solution of the phase problem has been found, and ii) the fact that most of them ignore the physics of the imaging process. Here, we present PhaseGAN, a new DL approach based on Generative Adversarial Networks, which allows the use of unpaired datasets and includes the physics of image formation. The performance of our approach is enhanced by including the image formation physics and a novel Fourier loss function, providing phase reconstructions when conventional phase retrieval algorithms fail, such as ultra-fast experiments. Thus, PhaseGAN offers the opportunity to address the phase problem in real-time when no phase reconstructions but good simulations or data from other experiments are available.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Optics Express
volume
29
issue
13
pages
12 pages
publisher
Optical Society of America
external identifiers
  • scopus:85107493582
  • pmid:34266067
ISSN
1094-4087
DOI
10.1364/OE.423222
language
English
LU publication?
yes
id
0a016771-146d-4a96-88cf-72ef201e809b
date added to LUP
2021-06-24 16:11:20
date last changed
2024-06-15 12:56:30
@article{0a016771-146d-4a96-88cf-72ef201e809b,
  abstract     = {{<p>Phase retrieval approaches based on deep learning (DL) provide a framework to obtain phase information from an intensity hologram or diffraction pattern in a robust manner and in real-time. However, current DL architectures applied to the phase problem rely on i) paired datasets, i. e., they are only applicable when a satisfactory solution of the phase problem has been found, and ii) the fact that most of them ignore the physics of the imaging process. Here, we present PhaseGAN, a new DL approach based on Generative Adversarial Networks, which allows the use of unpaired datasets and includes the physics of image formation. The performance of our approach is enhanced by including the image formation physics and a novel Fourier loss function, providing phase reconstructions when conventional phase retrieval algorithms fail, such as ultra-fast experiments. Thus, PhaseGAN offers the opportunity to address the phase problem in real-time when no phase reconstructions but good simulations or data from other experiments are available.</p>}},
  author       = {{Zhang, Yuhe and Noack, Mike Andreas and Vagovic, Patrik and Fezzaa, Kamel and Garcia-Moreno, Francisco and Ritschel, Tobias and Villanueva-Perez, Pablo}},
  issn         = {{1094-4087}},
  language     = {{eng}},
  month        = {{06}},
  number       = {{13}},
  pages        = {{19593--19604}},
  publisher    = {{Optical Society of America}},
  series       = {{Optics Express}},
  title        = {{PhaseGAN : a deep-learning phase-retrieval approach for unpaired datasets}},
  url          = {{http://dx.doi.org/10.1364/OE.423222}},
  doi          = {{10.1364/OE.423222}},
  volume       = {{29}},
  year         = {{2021}},
}