{
  "abstract": "High-resolution volumetric medical imaging is critical for clinical diagnosis, yet acquisition is often limited by scanner hardware, scan time, and for CT, radiation dose. Medical 3D Super-Resolution (Med3DSR) offers a computational alternative, but existing methods commonly rely on per-subject optimization, pretrained priors, or coordinate-based implicit representations, which compromise anatomical fidelity and limit efficiency. To address these limitations, we present MedGSSR, a fully end-to-end feed-forward framework that represents volumes as an explicit 3D Gaussian field for Med3DSR. Unlike coordinate-based implicit functions, our explicit 3D Gaussian representation naturally enhances signal continuity and local high-frequency fidelity. Specifically, MedGSSR explicitly decouples the reconstruction process into coarse-grained structural preservation and fine-grained textural refinement through the proposed Pyramid Anatomical Encoder and a Hierarchical Gaussian Projector. To support arbitrary-scale super-resolution, we introduce sub-voxel Gaussian decomposition and a Differentiable Gaussian Voxelizer that directly queries the continuous 3D intensity field, reducing discretization artifacts. Extensive experiments on MRI and CT benchmarks demonstrate that MedGSSR significantly outperforms state-of-the-art methods. Notably, our framework exhibits robust generalizability across unseen datasets without requiring per-subject optimization, enabling fast inference and high-fidelity volumetric super-resolution in practical clinical settings. Our project webpage, including code, is at https://william2ai.github.io/medgssr",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.06874",
  "author_total": 10,
  "authors": [
    {
      "name": "Chengkai Wang"
    },
    {
      "name": "Luoyu Hong"
    },
    {
      "name": "Yiting Zhao"
    },
    {
      "name": "Jiamin Wang"
    },
    {
      "name": "Xiang Feng"
    },
    {
      "name": "Feiwei Qin"
    },
    {
      "name": "Zhenzhong Kuang"
    },
    {
      "name": "Xuefei Yin"
    },
    {
      "name": "Ali Bashashati"
    },
    {
      "name": "Yanming Zhu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1q282cfkt6mcp.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.06874",
  "fulltext_url": null,
  "id": "1q282cfkt6mcp",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.06874",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CE"
    ],
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "eess.IV"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2609.06874",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-06",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/1q282cfkt6mcp.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:02Z",
      "native_id": "2609.06874",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.06874"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "MedGSSR: Generalizable Medical Image Super-Resolution 3D Reconstruction via Hierarchical Feed-forward Gaussian Splatting",
  "title_text": "MedGSSR: Generalizable Medical Image Super-Resolution 3D Reconstruction via Hierarchical Feed-forward Gaussian Splatting",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:02Z",
  "url": "https://research.draconitic.com/paper/1q282cfkt6mcp",
  "venue": "arXiv",
  "versions": []
}