An Optimal Control Approach for Deformable Registration
Abstract
This paper addresses large-displacement-diffeomorphic mapping registration from an optimal control perspective. This viewpoint leads to two complementary formulations. One approach requires the explicit computation of coordinate maps, whereas the other is formulated strictly in the image domain (thus making it also applicable to manifolds which require multiple coordinate charts). We discuss their intrinsic relation as well as the advantages and disadvantages of the two approaches. Further, we propose a novel formulation for unbiased image registration, which naturally extends to the case of time-series of images. We discuss numerical implementation details and carefully evaluate the properties of the alternative algorithms.
Cite
Text
Hart et al. "An Optimal Control Approach for Deformable Registration." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2009. doi:10.1109/CVPRW.2009.5204344Markdown
[Hart et al. "An Optimal Control Approach for Deformable Registration." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2009.](https://mlanthology.org/cvprw/2009/hart2009cvprw-optimal/) doi:10.1109/CVPRW.2009.5204344BibTeX
@inproceedings{hart2009cvprw-optimal,
title = {{An Optimal Control Approach for Deformable Registration}},
author = {Hart, Gabriel L. and Zach, Christopher and Niethammer, Marc},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2009},
pages = {9-16},
doi = {10.1109/CVPRW.2009.5204344},
url = {https://mlanthology.org/cvprw/2009/hart2009cvprw-optimal/}
}