Salvato in:
Dettagli Bibliografici
Autori principali: Suh, Yehyun, Martin, J. Ryan, Moyer, Daniel
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.07767
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909904586932224
author Suh, Yehyun
Martin, J. Ryan
Moyer, Daniel
author_facet Suh, Yehyun
Martin, J. Ryan
Moyer, Daniel
contents This paper presents an approach for improving 2D/3D pelvis registration in optimization-based pose estimators using a learned initialization function. Current methods often fail to converge to the optimal solution when initialized naively. We find that even a coarse initializer greatly improves pose estimator accuracy, and improves overall computational efficiency. This approach proves to be effective also in challenging cases under more extreme pose variation. Experimental validation demonstrates that our method consistently achieves robust and accurate registration, enhancing the reliability of 2D/3D registration for clinical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2503_07767
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Regression-based Pelvic Pose Initialization for Fast and Robust 2D/3D Pelvis Registration
Suh, Yehyun
Martin, J. Ryan
Moyer, Daniel
Computer Vision and Pattern Recognition
This paper presents an approach for improving 2D/3D pelvis registration in optimization-based pose estimators using a learned initialization function. Current methods often fail to converge to the optimal solution when initialized naively. We find that even a coarse initializer greatly improves pose estimator accuracy, and improves overall computational efficiency. This approach proves to be effective also in challenging cases under more extreme pose variation. Experimental validation demonstrates that our method consistently achieves robust and accurate registration, enhancing the reliability of 2D/3D registration for clinical applications.
title Regression-based Pelvic Pose Initialization for Fast and Robust 2D/3D Pelvis Registration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.07767