Saved in:
Bibliographic Details
Main Authors: Vati, Ines, Bourgeat, Pierrick, Cruz, Rodrigo Santa, Dore, Vincent, Salvado, Olivier, Fookes, Clinton, Lebrat, Léo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.19042
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915757495943168
author Vati, Ines
Bourgeat, Pierrick
Cruz, Rodrigo Santa
Dore, Vincent
Salvado, Olivier
Fookes, Clinton
Lebrat, Léo
author_facet Vati, Ines
Bourgeat, Pierrick
Cruz, Rodrigo Santa
Dore, Vincent
Salvado, Olivier
Fookes, Clinton
Lebrat, Léo
contents We introduce neural cortical maps, a continuous and compact neural representation for cortical feature maps, as an alternative to traditional discrete structures such as grids and meshes. It can learn from meshes of arbitrary size and provide learnt features at any resolution. Neural cortical maps enable efficient optimization on the sphere and achieve runtimes up to 30 times faster than classic barycentric interpolation (for the same number of iterations). As a proof of concept, we investigate rigid registration of cortical surfaces and propose NC-Reg, a novel iterative algorithm that involves the use of neural cortical feature maps, gradient descent optimization and a simulated annealing strategy. Through ablation studies and subject-to-template experiments, our method demonstrates sub-degree accuracy ($<1^\circ$ from the global optimum), and serves as a promising robust pre-alignment strategy, which is critical in clinical settings.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19042
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NC-Reg : Neural Cortical Maps for Rigid Registration
Vati, Ines
Bourgeat, Pierrick
Cruz, Rodrigo Santa
Dore, Vincent
Salvado, Olivier
Fookes, Clinton
Lebrat, Léo
Computer Vision and Pattern Recognition
We introduce neural cortical maps, a continuous and compact neural representation for cortical feature maps, as an alternative to traditional discrete structures such as grids and meshes. It can learn from meshes of arbitrary size and provide learnt features at any resolution. Neural cortical maps enable efficient optimization on the sphere and achieve runtimes up to 30 times faster than classic barycentric interpolation (for the same number of iterations). As a proof of concept, we investigate rigid registration of cortical surfaces and propose NC-Reg, a novel iterative algorithm that involves the use of neural cortical feature maps, gradient descent optimization and a simulated annealing strategy. Through ablation studies and subject-to-template experiments, our method demonstrates sub-degree accuracy ($<1^\circ$ from the global optimum), and serves as a promising robust pre-alignment strategy, which is critical in clinical settings.
title NC-Reg : Neural Cortical Maps for Rigid Registration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.19042