Metraipolis › archive › dc_815832ef2f2d

Physics-Guided Flow Matching for CT Image Reconstruction — arXiv:2608.28256

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28256
License (as archived)
CC0-1.0
Archived
2026-10-17T10:47:32.429Z
SHA-256 of the archived text
07f4b145ce80fb605720eeb725a6c130a8172736092b0297e6143b321c8032a8
Stable URL of this page
https://metraipolis.com/documento/dc_815832ef2f2d

How to cite

Physics-Guided Flow Matching for CT Image Reconstruction — arXiv:2608.28256 — arXiv (en), https://arxiv.org/abs/2608.28256 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_815832ef2f2d (Metraipolis archive dc_815832ef2f2d, sha256 07f4b145ce80fb605720eeb725a6c130a8172736092b0297e6143b321c8032a8)
BibTeX
@misc{dc815832ef2f2d,
  title = {Physics-Guided Flow Matching for CT Image Reconstruction — arXiv:2608.28256},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28256},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_815832ef2f2d; sha256 07f4b145ce80fb605720eeb725a6c130a8172736092b0297e6143b321c8032a8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28256. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep generative models have recently emerged as powerful priors for solving ill-posed inverse problems in CT, with diffusion-based approaches achieving state-of-the-art reconstruction performance. However, diffusion models typically rely on stochastic sampling procedures, long inference trajectories, and carefully tuned noise schedules, which can limit computational efficiency and numerical stability, especially at high spatial resolutions. In this work, we investigate Flow Matching as an alternative generative prior for CT reconstruction. We train a high-resolution Rectified Flow Matching model on 256x256 chest images from the Mayo Clinic Low-Dose CT dataset. To mitigate overfitting and limited anatomical variability, we employ a two-stage training strategy consisting of an initial phase with strong, anatomically informed data augmentation, followed by a fine-tuning phase with reduced or no augmentation to refine structural fidelity. The resulting model is capable of generating high-quality and anatomically coherent CT-like images, serving as a strong learned prior. We then evaluate multiple reconstruction methods specifically designed for Flow Matching models, including Plug-and-Play Flow, FlowDPS, Flower, and Flow-Priors (ICTM), and compare them against state-of-the-art diffusion-based reconstruction algorithms such as DDRM, DPS, and DiffPIR. Experimental results across several CT inverse problem settings show that Flow Matching-based approaches consistently outperform diffusion-based methods in terms of PSNR, SSIM, and perceptual quality, while requiring fewer sampling steps. Finally, we publicly release the trained Flow Matching model and accompanying code to facilitate reproducibility and future research. Overall, this work demonstrates that Flow Matching provides a stable, efficient, and effective alternative to diffusion models for high-resolution CT image reconstruction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.28256 — 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 2026-10-17T10:33:42.409Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).