{
  "abstract": "Light field angular super-resolution (LFASR) seeks to recover missing viewpoints from sparsely captured angular samples, while preserving the underlying scene structure across views. This task is complicated by disparity-induced variations, incomplete visibility near occlusion boundaries, and view-dependent appearance changes caused by reflective surfaces. In this work, we propose a cross-domain EPI–spatial–angular (X-ESA) framework that combines EPI-based geometric modeling with complementary spatial and angular feature extraction. A CSWin-based EPI transformer captures long-range, slope-aligned dependencies, while dedicated convolutional branches refine spatial details and cross-view relationships. These features are integrated through a mesh–progressive fusion strategy, followed by channel attention and spatial residual refinement. Experiments on real-world and synthetic datasets under the 2×2→7×7 setting result in average performances of 41.29 dB/0.989 SSIM and 40.98 dB/0.989 SSIM, respectively. The proposed model contains 2.84 M trainable parameters and provides competitive reconstruction quality relative to existing LFASR methods.",
  "abstract_shown": true,
  "affiliations": [
    "School of Electronics Engineering, College of Electrical and Computer Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea",
    "Information Technology Department, Faculty of Computers and Information, Assiut University, Assiut 71526, Egypt",
    "Electrical Engineering Department, Faculty of Engineering, Assiut University, Assiut 71526, Egypt",
    "School of Information and Communication Engineering, College of Electrical and Computer Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Ebrahem Elkady",
      "orcid": "0000-0002-7248-8880"
    },
    {
      "affs": [
        2
      ],
      "name": "Ahmed Salem",
      "orcid": "0000-0002-4682-0368"
    },
    {
      "affs": [
        3
      ],
      "name": "Hyun-Soo Kang",
      "orcid": "0000-0002-4333-2852"
    },
    {
      "affs": [
        0
      ],
      "name": "Jae-Won Suh"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5z5s501d4tpb0.bib",
  "cited_by": 0,
  "doi": "10.3390/math14203811",
  "fulltext_url": null,
  "id": "5z5s501d4tpb0",
  "issns": [
    "2227-7390"
  ],
  "landing_url": "https://www.mdpi.com/2227-7390/14/20/3811",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1707|Advanced Vision and Imaging"
    ]
  ],
  "openalex": "W7213334270",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-20",
  "publisher": "MDPI AG",
  "ris": "https://research.draconitic.com/paper/5z5s501d4tpb0.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:29Z",
      "native_id": "10.3390/math14203811",
      "source": "crossref",
      "url": "https://www.mdpi.com/2227-7390/14/20/3811"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "issn:2227-7390",
      "subfield": "general"
    }
  ],
  "title": "Cross-Domain Mesh–Progressive Fusion for Light Field Reconstruction",
  "title_text": "Cross-Domain Mesh–Progressive Fusion for Light Field Reconstruction",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:18:29Z",
  "url": "https://research.draconitic.com/paper/5z5s501d4tpb0",
  "venue": "Mathematics",
  "versions": []
}