Metraipolis › archive › dc_2b2c20cdaf61

Learning a Motion Manifold to Constrain Ambiguity in Unsupervised 4D Medical Image Interpolation — arXiv:2610.40121

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40121
License (as archived)
CC0-1.0
Archived
2026-11-01T02:42:19.348Z
SHA-256 of the archived text
5df00fd1201486af05367d8ef1dcf3cba40e447215e9cf13567a52d70a721ddd
Stable URL of this page
https://metraipolis.com/documento/dc_2b2c20cdaf61

How to cite

Learning a Motion Manifold to Constrain Ambiguity in Unsupervised 4D Medical Image Interpolation — arXiv:2610.40121 — arXiv (en), https://arxiv.org/abs/2610.40121 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b2c20cdaf61 (Metraipolis archive dc_2b2c20cdaf61, sha256 5df00fd1201486af05367d8ef1dcf3cba40e447215e9cf13567a52d70a721ddd)
BibTeX
@misc{dc2b2c20cdaf61,
  title = {Learning a Motion Manifold to Constrain Ambiguity in Unsupervised 4D Medical Image Interpolation — arXiv:2610.40121},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40121},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b2c20cdaf61; sha256 5df00fd1201486af05367d8ef1dcf3cba40e447215e9cf13567a52d70a721ddd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40121. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Unsupervised 4D medical image interpolation reconstructs intermediate anatomical states from temporally sparse observations without intermediate supervision. Distinct motion fields may attain comparable endpoint agreement while producing different intermediate anatomy, giving rise to motion ambiguity. This ambiguity is difficult to constrain when many independently adjustable motion variables must be estimated from the observed endpoints. We develop a framework that learns a motion manifold to restrict candidate motion fields while retaining sample-specific variation. Cross-Sample Spectral Basis Learning extracts recurring motion structure from endpoint-derived dense estimates and encodes it in a shared spectral basis. Sample-Conditioned Cayley Basis Reorientation uses predicted motion coordinates to rotate the effective motion directions for each endpoint pair without increasing the number of independent coordinates. Their composition defines a nonlinear family of complete velocity fields across endpoint pairs, accommodating anatomical and motion-state differences within a restricted representation. Integrating each predicted field supports bidirectional reconstruction at arbitrary intermediate times. Theoretical analysis establishes sufficient conditions under which endpoint observations distinguish nearby motions within the learned family. Experiments on ACDC and 4D-Lung demonstrate state-of-the-art performance among the evaluated methods trained without intermediate volumes and competitive results against methods using intermediate supervision.

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/2610.40121 — 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 2026-11-01T02:16:43.972Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).