Metraipolis › archive › dc_75d0da183dbf
RARF: Region-Aware Rectified Flows for 3D Brain MRI Inpainting — arXiv:2609.03956
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03956
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T01:12:11.640Z
- SHA-256 of the archived text
083978310b356c54208369bc635f503f6125a7eba9bb0cd63fdb3e822c44ab80- Stable URL of this page
https://metraipolis.com/documento/dc_75d0da183dbf
How to cite
RARF: Region-Aware Rectified Flows for 3D Brain MRI Inpainting — arXiv:2609.03956 — arXiv (en), https://arxiv.org/abs/2609.03956 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75d0da183dbf (Metraipolis archive dc_75d0da183dbf, sha256 083978310b356c54208369bc635f503f6125a7eba9bb0cd63fdb3e822c44ab80)
BibTeX
@misc{dc75d0da183dbf,
title = {RARF: Region-Aware Rectified Flows for 3D Brain MRI Inpainting — arXiv:2609.03956},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03956},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75d0da183dbf; sha256 083978310b356c54208369bc635f503f6125a7eba9bb0cd63fdb3e822c44ab80},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03956. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Medical image inpainting has the potential to improve automated brain MRI analysis by reconstructing healthy tissue within pathological regions. We introduce RARF, a task-agnostic region-aware rectified flow framework for masked data generation. We instantiate the framework for 3D brain MRI inpainting as our submission to the BraTS Inpainting Challenge 2026. RARF restricts the stochastic interpolation process to the inpainting region, while the observed voxels remain fixed and provide patient-specific anatomical context. A three-dimensional neural network receives the partially voided image, with Gaussian noise filling the missing region, together with the inpainting mask and the corresponding timestep. The model is trained using masked flow-matching and reconstruction-consistency objectives, combined with mask-aware preprocessing and data augmentation. During inference, the learned velocity field transports the initial noise toward a plausible reconstruction of the missing tissue, which is then combined with the unchanged observed anatomy. Experiments under the BraTS evaluation protocol show that the proposed approach produces competitive reconstructions while maintaining anatomical consistency. Source code is available at: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.03956 — 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 2026-10-17T00:28:03.017Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).