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

• Published in: Advanced Physics Research Vol. 4; no. 2
• Main Authors: Chen, Yu‐Chen, Shen, Li‐Hua, Qi, Bote, Li, Yu‐Hua, Hu, Xiao‐Bo, Chew, Khian‐Hooi, Chen, Rui‐Pin, He, Sailing
• Format: Journal Article
• Language: English
• Published: Edinburgh John Wiley & Sons, Inc 01.02.2025; Wiley-VCH
• Subjects: Deep learning; Neural networks; Phase distribution; Physics; Polarization; P‐DenseUnet framework; Reconstruction; Scattering; scattering medium; Speckle patterns; Transfer matrices; vector beam; vector reconstruction of orthogonal polarization components; vector transfer matrix
• ISSN: 2751-1200; 2751-1200
• DOI: 10.1002/apxr.202400023

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. The vector reconstruction of the orthogonal polarization components in a structured optical field passing through scattering media based on deep learning is demonstrated. The phase images of orthogonal polarization components can be reconstructed from a speckle pattern by P‐DenseUnet. This proposed method provides a solution to simultaneously restore the orthogonal polarization components in a structured optical field passing through scattering media.