{
  "abstract": "High-resolution three-dimensional (3-D) medical latent diffusion remains limited by the cost of decoding full volumes, which existing latent autoencoders (AEs) handle through overlapping sub-volume decoding. We propose a continuous 3-D latent diffusion model framework for computed tomography (CT) and magnetic resonance imaging (MRI) generation and measurement-guided reconstruction, built on a coordinate-rendering autoencoder (CoRe-AE). Its decoder applies its convolutional stage once on the compact latent grid and renders voxel intensities from spatial coordinates through a lightweight implicit head, evaluated in memory-bounded chunks. This design avoids overlapping sub-volumes and remains differentiable with respect to the latent, so that the decoder can be used inside measurement-guided reconstruction. The framework was evaluated on CT volumes of 512\\textsuperscript{3} voxels and MRI volumes of 256\\textsuperscript{3} voxels. At 512\\textsuperscript{3}, the decoder was 4--18 times faster than the MAISI and 3D MedDiffusion AEs and required the lowest peak graphics processing unit (GPU) memory, including when its gradient was computed. CoRe-AE also achieved the highest peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) among the evaluated AEs on both modalities. The resulting frozen 3-D latent prior generated full volumes without patch seams and, without retraining, reconstructed sparse-view CT and accelerated MRI through hard data consistency, within 2.4--4.9 dB PSNR of the pixel-domain decomposed diffusion sampler (DDS). A single volumetric latent prior thus supports both generation and reconstruction of high-resolution medical volumes on one GPU. Our code will be made available at https://github.com/Mellak/continuous-3d-latent-diffusion/.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2607.16491",
  "author_total": 4,
  "authors": [
    {
      "name": "Youness Mellak"
    },
    {
      "name": "Antoine De Paepe"
    },
    {
      "name": "Dimitris Visvikis"
    },
    {
      "name": "Alexandre Bousse"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/38ry60jqk5b10.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2607.16491",
  "fulltext_url": null,
  "id": "38ry60jqk5b10",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2607.16491",
  "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",
      "physics.med-ph"
    ],
    [
      "openalex",
      "1707|Generative Adversarial Networks and Image Synthesis"
    ]
  ],
  "openalex": "W7169892871",
  "pdf_url": "https://arxiv.org/pdf/2607.16491",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-12",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/38ry60jqk5b10.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:06Z",
      "native_id": "2607.16491",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2607.16491"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.med-ph",
      "subfield": "biological-medical"
    }
  ],
  "title": "Continuous 3-D Latent Diffusion for Medical Image Generation and Reconstruction",
  "title_text": "Continuous 3-D Latent Diffusion for Medical Image Generation and Reconstruction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:06Z",
  "url": "https://research.draconitic.com/paper/38ry60jqk5b10",
  "venue": "arXiv",
  "versions": []
}