analiza aiqbench
The paper extends implicit neural representations (INRs), small coordinate-based networks, to deformable registration of periodic medical image sequences. A single network predicts deformations for all frames, and a temporal consistency loss enforces agreement between direct and multi-hop transformations. On the DIR-LAB lung CT benchmark it reports a 1.03 mm target registration error, which the authors say beats other INR-based methods, though it is a single benchmark and not a clinical validation. Readers working on lightweight neural methods or medical imaging may find the consistency-loss idea transferable, and the public code makes the claim checkable.
Temporal Periodic Image Registration with Implicit Neural Representations
arXiv:2610.21845v1 Announce Type: cross Abstract: 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 https://github.com/MMLowes/Temporal_INR.
Abstract: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.
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2610.21845 [cs.CV]
(or arXiv:2610.21845v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.21845 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1007/978-3-032-09513-8_43 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 270 cuvinte
Subiecte conexe
Composed Historical Image Retrieval by Modeling Temporal Representations
arXiv · 21 aug. 2026
A Query-Efficient Stochastic Volume Rendering Framework for Time-Varying Implicit Neural Volumes
arXiv · 31 iul. 2026
Learnable Spectral Activations
arXiv · 7 oct. 2026
SRT: Super-Resolution for Time Series via Disentangled Rectified Flow
arXiv · 9 iun. 2026