Metraipolis › archive › dc_dc8bb3ad339f

PhyDiCT: Plug-and-Play CT Reconstruction from Sparse X-Rays via Differentiable Rendering and Strong Priors — arXiv:2610.09253

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09253
License (as archived)
CC0-1.0
Archived
2026-10-08T12:47:03.898Z
SHA-256 of the archived text
bc0c4bb0b8042511edc225b096e4ab2506bfbfde64af388c95ee2aa958af4524
Stable URL of this page
https://metraipolis.com/documento/dc_dc8bb3ad339f

How to cite

PhyDiCT: Plug-and-Play CT Reconstruction from Sparse X-Rays via Differentiable Rendering and Strong Priors — arXiv:2610.09253 — arXiv (en), https://arxiv.org/abs/2610.09253 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc8bb3ad339f (Metraipolis archive dc_dc8bb3ad339f, sha256 bc0c4bb0b8042511edc225b096e4ab2506bfbfde64af388c95ee2aa958af4524)
BibTeX
@misc{dcdc8bb3ad339f,
  title = {PhyDiCT: Plug-and-Play CT Reconstruction from Sparse X-Rays via Differentiable Rendering and Strong Priors — arXiv:2610.09253},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09253},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc8bb3ad339f; sha256 bc0c4bb0b8042511edc225b096e4ab2506bfbfde64af388c95ee2aa958af4524},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09253. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reconstructing 3D Computed Tomography (CT) images from a few X-ray projections is a highly ill-posed inverse problem due to the loss of volumetric information. We propose PhyDiCT, a training-free framework that integrates a differentiable Physics-based forward model, grounded in the Beer-Lambert law, with a text-conditioned Diffusion as a strong prior to reconstruct 3D lung CT images. We refer to our approach as training-free since the prior model is used without fine-tuning, and our goal is to steer the denoising procedure to generate samples consistent with X-ray observations. We guide the diffusion generation using Split Gibbs sampling to jointly optimize for projection fidelity (reward) and consistency with prior knowledge. Also, we introduce a test-time refinement step that enhances image realism and anatomical coherence. We extensively evaluate our method on publicly available 3D CT datasets using both perceptual and semantic metrics, demonstrating that it surpasses existing plug-and-play diffusion and fully trained reconstruction approaches. Our findings highlight that combining a strong generative prior with the underlying physics of image formation substantially improves reconstruction quality, e.g., 7.5\% improvement on SSIM compared to full training methods. Code will be released at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.09253 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:18:15.323Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).