Deep Plug-and-Play HIO Approach for Phase Retrieval

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Isil, Cagatay, Oktem, Figen S.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908187775467520
author Isil, Cagatay
Oktem, Figen S.
author_facet Isil, Cagatay
Oktem, Figen S.
contents In the phase retrieval problem, the aim is the recovery of an unknown image from intensity-only measurements such as Fourier intensity. Although there are several solution approaches, solving this problem is challenging due to its nonlinear and ill-posed nature. Recently, learning-based approaches have emerged as powerful alternatives to the analytical methods for several inverse problems. In the context of phase retrieval, a novel plug-and-play approach that exploits learning-based prior and efficient update steps has been presented at the Computational Optical Sensing and Imaging topical meeting, with demonstrated state-of-the-art performance. The key idea was to incorporate learning-based prior to the Gerchberg-Saxton type algorithms through plug-and-play regularization. In this paper, we present the mathematical development of the method including the derivation of its analytical update steps based on half-quadratic splitting and comparatively evaluate its performance through extensive simulations on a large test dataset. The results show the effectiveness of the method in terms of both image quality, computational efficiency, and robustness to initialization and noise.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18967
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Plug-and-Play HIO Approach for Phase Retrieval
Isil, Cagatay
Oktem, Figen S.
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
In the phase retrieval problem, the aim is the recovery of an unknown image from intensity-only measurements such as Fourier intensity. Although there are several solution approaches, solving this problem is challenging due to its nonlinear and ill-posed nature. Recently, learning-based approaches have emerged as powerful alternatives to the analytical methods for several inverse problems. In the context of phase retrieval, a novel plug-and-play approach that exploits learning-based prior and efficient update steps has been presented at the Computational Optical Sensing and Imaging topical meeting, with demonstrated state-of-the-art performance. The key idea was to incorporate learning-based prior to the Gerchberg-Saxton type algorithms through plug-and-play regularization. In this paper, we present the mathematical development of the method including the derivation of its analytical update steps based on half-quadratic splitting and comparatively evaluate its performance through extensive simulations on a large test dataset. The results show the effectiveness of the method in terms of both image quality, computational efficiency, and robustness to initialization and noise.
title Deep Plug-and-Play HIO Approach for Phase Retrieval
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2411.18967