Metraipolis › archive › dc_ed15288489d7

Temporal Periodic Image Registration with Implicit Neural Representations — arXiv:2610.21845

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21845
License (as archived)
CC0-1.0
Archived
2026-10-16T10:25:17.353Z
SHA-256 of the archived text
4e7af921ebee8675c1129a595ce3072429f918705c9b2e963c37bd564b3b6529
Stable URL of this page
https://metraipolis.com/documento/dc_ed15288489d7

How to cite

Temporal Periodic Image Registration with Implicit Neural Representations — arXiv:2610.21845 — arXiv (en), https://arxiv.org/abs/2610.21845 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed15288489d7 (Metraipolis archive dc_ed15288489d7, sha256 4e7af921ebee8675c1129a595ce3072429f918705c9b2e963c37bd564b3b6529)
BibTeX
@misc{dced15288489d7,
  title = {Temporal Periodic Image Registration with Implicit Neural Representations — arXiv:2610.21845},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21845},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed15288489d7; sha256 4e7af921ebee8675c1129a595ce3072429f918705c9b2e963c37bd564b3b6529},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21845. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Implicit Neural Representations (INRs) have recently gained popularity for their ability to model functions using simple and lightweight networks. These methods have also proven effective in deformable image registration. In this work, we extend INRs for deformable image registration to the domain of temporal image registration, focusing on periodic temporal image sequences. Our approach, Temporal-IDIR, optimizes a single INR to model deformations across all frames in a temporal image sequence simultaneously, allowing for self-regularization through its own deformation predictions. To achieve this, we introduce a temporal consistency loss that penalizes discrepancies between direct source-to-target transformations and those traversing intermediate frames. We evaluate our framework on the DIR-LAB dataset, using the target registration error (TRE) between annotated and moved landmarks as the metric. Here, we achieve a TRE of 1.03 mm, outperforming other INR-based registration methods. Additionally, our framework supports smooth interpolation between time frames by estimating deformations between the given input frames. Code is publicly available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.21845 — 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 2026-10-16T08:48:02.924Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).