{
  "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.16938",
  "author_total": 6,
  "authors": [
    {
      "name": "Qianqian He"
    },
    {
      "name": "Kenan Guo"
    },
    {
      "name": "Jumin Qiu"
    },
    {
      "name": "Huifu Qiu"
    },
    {
      "name": "Shuyuan Xiao"
    },
    {
      "name": "Tingting Liu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bt3nv8zq1jyth.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.16938",
  "fulltext_url": null,
  "id": "bt3nv8zq1jyth",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.16938",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "physics.app-ph"
    ],
    [
      "arxiv",
      "physics.optics"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2606.16938",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-17",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bt3nv8zq1jyth.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:30:52Z",
      "native_id": "2606.16938",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.16938"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.app-ph",
      "subfield": "applied-instrumentation"
    },
    {
      "field": "physics",
      "origin": "arxiv:physics.optics",
      "subfield": "optics-photonics"
    }
  ],
  "title": "Edge-enhanced diffractive neural networks based on spin-multiplexed nonlocal metasurfaces",
  "title_text": "Edge-enhanced diffractive neural networks based on spin-multiplexed nonlocal metasurfaces",
  "type": "preprint",
  "updated_at": "2026-11-04T15:20:50Z",
  "url": "https://research.draconitic.com/paper/bt3nv8zq1jyth",
  "venue": "arXiv",
  "versions": [
    {
      "doi": "10.1103/gwny-d6fw",
      "pid": null,
      "relation": "published-as",
      "title": null,
      "venue": null
    }
  ]
}