Learning‐Based Vectorial Reconstruction of Orthogonal Polarization Components in a Structured Vector Optical Field Passing Through Scattering Media

Abstract Optical imaging through scattering media has become important due to its fundamental physics interest and various applications. The reconstruction of a structured optical field with various states of polarization passing through a scattering medium with a speckle pattern behind the scatteri...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu‐Chen Chen, Li‐Hua Shen, Bote Qi, Yu‐Hua Li, Xiao‐Bo Hu, Khian‐Hooi Chew, Rui‐Pin Chen, Sailing He
Format: Article
Language:English
Published: Wiley-VCH 2025-02-01
Series:Advanced Physics Research
Subjects:
Online Access:https://doi.org/10.1002/apxr.202400023
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762681072910336
author Yu‐Chen Chen
Li‐Hua Shen
Bote Qi
Yu‐Hua Li
Xiao‐Bo Hu
Khian‐Hooi Chew
Rui‐Pin Chen
Sailing He
author_facet Yu‐Chen Chen
Li‐Hua Shen
Bote Qi
Yu‐Hua Li
Xiao‐Bo Hu
Khian‐Hooi Chew
Rui‐Pin Chen
Sailing He
author_sort Yu‐Chen Chen
collection DOAJ
description Abstract Optical imaging through scattering media has become important due to its fundamental physics interest and various applications. The reconstruction of a structured optical field with various states of polarization passing through a scattering medium with a speckle pattern behind the scattering medium remains challenging since existing restoring techniques only reconstruct the speckle in a single‐polarization state (scalar optical field). This work proposes a novel approach to simultaneously restore the initial orthogonally polarized components from a speckle pattern behind a scattering medium. The neural network Polarization‐DenseUnet (P‐DenseUnet) based on the vector transfer matrix is constructed to restore the two orthogonally linear (or circular) polarization components of a structured vector optical field from a speckle pattern behind the scattering medium. The generalization and effectiveness of this proposed method are tested for high fidelity with different phase distributions such as vortex, digits, and Fashion‐mnist.
format Article
id doaj-art-07e7c8ae069849d8933e6c16b1077ef1
institution DOAJ
issn 2751-1200
language English
publishDate 2025-02-01
publisher Wiley-VCH
record_format Article
series Advanced Physics Research
spelling doaj-art-07e7c8ae069849d8933e6c16b1077ef12025-08-20T03:05:41ZengWiley-VCHAdvanced Physics Research2751-12002025-02-0142n/an/a10.1002/apxr.202400023Learning‐Based Vectorial Reconstruction of Orthogonal Polarization Components in a Structured Vector Optical Field Passing Through Scattering MediaYu‐Chen Chen0Li‐Hua Shen1Bote Qi2Yu‐Hua Li3Xiao‐Bo Hu4Khian‐Hooi Chew5Rui‐Pin Chen6Sailing He7Key Laboratory of Optical Field Manipulation of Zhejiang Province Department of Physics Zhejiang Sci‐Tech University Hangzhou 310018 ChinaKey Laboratory of Optical Field Manipulation of Zhejiang Province Department of Physics Zhejiang Sci‐Tech University Hangzhou 310018 ChinaKey Laboratory of Optical Field Manipulation of Zhejiang Province Department of Physics Zhejiang Sci‐Tech University Hangzhou 310018 ChinaKey Laboratory of Optical Field Manipulation of Zhejiang Province Department of Physics Zhejiang Sci‐Tech University Hangzhou 310018 ChinaKey Laboratory of Optical Field Manipulation of Zhejiang Province Department of Physics Zhejiang Sci‐Tech University Hangzhou 310018 ChinaKey Laboratory of Optical Field Manipulation of Zhejiang Province Department of Physics Zhejiang Sci‐Tech University Hangzhou 310018 ChinaKey Laboratory of Optical Field Manipulation of Zhejiang Province Department of Physics Zhejiang Sci‐Tech University Hangzhou 310018 ChinaCentre for Optical and Electromagnetic Research Joint Research Center of Photonics of the Royal Institute of Technology (Sweden) and Zhejiang University (China) Zhejiang University Hangzhou 310058 ChinaAbstract Optical imaging through scattering media has become important due to its fundamental physics interest and various applications. The reconstruction of a structured optical field with various states of polarization passing through a scattering medium with a speckle pattern behind the scattering medium remains challenging since existing restoring techniques only reconstruct the speckle in a single‐polarization state (scalar optical field). This work proposes a novel approach to simultaneously restore the initial orthogonally polarized components from a speckle pattern behind a scattering medium. The neural network Polarization‐DenseUnet (P‐DenseUnet) based on the vector transfer matrix is constructed to restore the two orthogonally linear (or circular) polarization components of a structured vector optical field from a speckle pattern behind the scattering medium. The generalization and effectiveness of this proposed method are tested for high fidelity with different phase distributions such as vortex, digits, and Fashion‐mnist.https://doi.org/10.1002/apxr.202400023P‐DenseUnet frameworkscattering mediumvector beamvector reconstruction of orthogonal polarization componentsvector transfer matrix
spellingShingle Yu‐Chen Chen
Li‐Hua Shen
Bote Qi
Yu‐Hua Li
Xiao‐Bo Hu
Khian‐Hooi Chew
Rui‐Pin Chen
Sailing He
Learning‐Based Vectorial Reconstruction of Orthogonal Polarization Components in a Structured Vector Optical Field Passing Through Scattering Media
Advanced Physics Research
P‐DenseUnet framework
scattering medium
vector beam
vector reconstruction of orthogonal polarization components
vector transfer matrix
title Learning‐Based Vectorial Reconstruction of Orthogonal Polarization Components in a Structured Vector Optical Field Passing Through Scattering Media
title_full Learning‐Based Vectorial Reconstruction of Orthogonal Polarization Components in a Structured Vector Optical Field Passing Through Scattering Media
title_fullStr Learning‐Based Vectorial Reconstruction of Orthogonal Polarization Components in a Structured Vector Optical Field Passing Through Scattering Media
title_full_unstemmed Learning‐Based Vectorial Reconstruction of Orthogonal Polarization Components in a Structured Vector Optical Field Passing Through Scattering Media
title_short Learning‐Based Vectorial Reconstruction of Orthogonal Polarization Components in a Structured Vector Optical Field Passing Through Scattering Media
title_sort learning based vectorial reconstruction of orthogonal polarization components in a structured vector optical field passing through scattering media
topic P‐DenseUnet framework
scattering medium
vector beam
vector reconstruction of orthogonal polarization components
vector transfer matrix
url https://doi.org/10.1002/apxr.202400023
work_keys_str_mv AT yuchenchen learningbasedvectorialreconstructionoforthogonalpolarizationcomponentsinastructuredvectoropticalfieldpassingthroughscatteringmedia
AT lihuashen learningbasedvectorialreconstructionoforthogonalpolarizationcomponentsinastructuredvectoropticalfieldpassingthroughscatteringmedia
AT boteqi learningbasedvectorialreconstructionoforthogonalpolarizationcomponentsinastructuredvectoropticalfieldpassingthroughscatteringmedia
AT yuhuali learningbasedvectorialreconstructionoforthogonalpolarizationcomponentsinastructuredvectoropticalfieldpassingthroughscatteringmedia
AT xiaobohu learningbasedvectorialreconstructionoforthogonalpolarizationcomponentsinastructuredvectoropticalfieldpassingthroughscatteringmedia
AT khianhooichew learningbasedvectorialreconstructionoforthogonalpolarizationcomponentsinastructuredvectoropticalfieldpassingthroughscatteringmedia
AT ruipinchen learningbasedvectorialreconstructionoforthogonalpolarizationcomponentsinastructuredvectoropticalfieldpassingthroughscatteringmedia
AT sailinghe learningbasedvectorialreconstructionoforthogonalpolarizationcomponentsinastructuredvectoropticalfieldpassingthroughscatteringmedia