Edge-enhanced diffractive neural networks based on spin-multiplexed nonlocal metasurfaces
Abstract
Single-layer diffractive neural networks often face classification accuracy bottlenecks due to limited wavefront modulation capabilities. Edge detection, as an optical image processing technique, extracts image contours and offers a promising way to simplify classification tasks. However, integrating edge detection and DNN-based classification on a single chip remains a challenge. Here, we propose an integrated nonlocal meta-platform that sequentially achieves all-optical edge detection and classification via spin-multiplexing. By exploiting the dispersion properties of the nonlocal Huygens' metasurface, the co-polarized component in the output light performs momentum-space filtering for real-time edge detection. Subsequently, the cross-polarized component undergoes geometric phase modulation to execute image classification within the DNN. We couple quasi-bound states in the continuum and magnetic dipole resonances in crescent-shaped nanopillars, achieving a high polarization conversion efficiency of approximately 55%. This edge-enhanced DNN architecture significantly reduces data redundancy, elevating the classification accuracy of the single-layer network on the MNIST dataset from 64.2% to 80.7%. Our work provides a compact, high-efficiency solution for integrated all-optical machine vision and intelligent photonic computing.
Versions
Related
- Meta-Optics-Based Diffractive Learning Machine for Angle-Multiplexed Multi-Task Processing
- Wavelength-Multiplexed Nonlinear Computing with a Single-Layer Diffractive Optical Processor
- Wavelength-Multiplexed 2D Beam Steering via a Passive Diffractive Network
- Thermal Holography with Nonlocal Metasurfaces
- Beyond the Thin-Layer Limit: Differentiable Volumetric Training for Visible-Range Diffractive Neural Networks
BibTeX
@misc{he2026edgeenhanced,
title = {{Edge-enhanced diffractive neural networks based on spin-multiplexed nonlocal metasurfaces}},
author = {Qianqian He and Kenan Guo and Jumin Qiu and Huifu Qiu and Shuyuan Xiao and Tingting Liu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.16938},
eprint = {2606.16938},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.16938},
}
RIS
TY - UNPB
TI - Edge-enhanced diffractive neural networks based on spin-multiplexed nonlocal metasurfaces
AU - Qianqian He
AU - Kenan Guo
AU - Jumin Qiu
AU - Huifu Qiu
AU - Shuyuan Xiao
AU - Tingting Liu
PY - 2026
DA - 2026/10/17
PB - arXiv
DO - 10.48550/arxiv.2606.16938
UR - https://arxiv.org/abs/2606.16938
AB - Single-layer diffractive neural networks often face classification accuracy bottlenecks due to limited wavefront modulation capabilities. Edge detection, as an optical image processing technique, extracts image contours and offers a promising way to simplify classification tasks. However, integrating edge detection and DNN-based classification on a single chip remains a challenge. Here, we propose an integrated nonlocal meta-platform that sequentially achieves all-optical edge detection and classification via spin-multiplexing. By exploiting the dispersion properties of the nonlocal Huygens' metasurface, the co-polarized component in the output light performs momentum-space filtering for real-time edge detection. Subsequently, the cross-polarized component undergoes geometric phase modulation to execute image classification within the DNN. We couple quasi-bound states in the continuum and magnetic dipole resonances in crescent-shaped nanopillars, achieving a high polarization conversion efficiency of approximately 55%. This edge-enhanced DNN architecture significantly reduces data redundancy, elevating the classification accuracy of the single-layer network on the MNIST dataset from 64.2% to 80.7%. Our work provides a compact, high-efficiency solution for integrated all-optical machine vision and intelligent photonic computing.
ER -