Metraipolis › archive › dc_fd9fd66b7970

Zero-Shot Brain MRI Inpainting with 2.5D Unconditional Flow Priors — arXiv:2610.08983

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08983
License (as archived)
CC0-1.0
Archived
2026-10-08T12:46:51.273Z
SHA-256 of the archived text
a58e5947fc25014be8b260cf5cd2b73ed6bd6ecd86d6d200c525df5d822d0d93
Stable URL of this page
https://metraipolis.com/documento/dc_fd9fd66b7970

How to cite

Zero-Shot Brain MRI Inpainting with 2.5D Unconditional Flow Priors — arXiv:2610.08983 — arXiv (en), https://arxiv.org/abs/2610.08983 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd9fd66b7970 (Metraipolis archive dc_fd9fd66b7970, sha256 a58e5947fc25014be8b260cf5cd2b73ed6bd6ecd86d6d200c525df5d822d0d93)
BibTeX
@misc{dcfd9fd66b7970,
  title = {Zero-Shot Brain MRI Inpainting with 2.5D Unconditional Flow Priors — arXiv:2610.08983},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08983},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd9fd66b7970; sha256 a58e5947fc25014be8b260cf5cd2b73ed6bd6ecd86d6d200c525df5d822d0d93},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08983. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative inpainting of brain MRI volumes is essential for synthesizing healthy tissue in pathological regions, improving the accuracy and reliability of automated downstream brain analysis applications such as image registration, brain extraction, and segmentation. However, standard 3D approaches are computationally prohibitive, while efficient 2D slice-wise methods suffer from severe inter-slice discontinuities. Furthermore, traditional models rely on conditional training, requiring task-specific learning of masked inputs. We propose a zero-shot brain MRI inpainting framework utilizing 2.5D unconditional flow priors to capture spatial context along the superior-inferior axis without the overhead of full 3D convolutions. During training, our flow matching model learns the joint distribution of adjacent axial slice triplets, modeling the manifold of healthy brain anatomy while explicitly excluding pathological regions from the loss function. At inference, the model processes the input triplets autoregressively along the depth axis. We employ the Restora-Flow solver to constrain the unconditional prior using the input mask, achieving accurate zero-shot inpainting. Evaluations show our 2.5D strategy resolves the structural discontinuities of 2D baselines, synthesizing plausible healthy tissue while maintaining volumetric consistency across the axial, sagittal, and coronal planes. As a final step, we generate and average an ensemble of multiple stochastic reconstructions to form the final prediction. Quantitative results benchmarked on the official BraTS 2026 Inpainting Challenge validation set demonstrate the effectiveness of our proposed approach, yielding an SSIM of 0.816 $\pm$ 0.112, MSE of 0.007 $\pm$ 0.005, and PSNR of 22.923 $\pm$ 4.343. Code is available 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/2610.08983 — 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 2026-10-08T12:18:15.278Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).