Non-Rigid Metric Shape and Motion Recovery from Uncalibrated Images Using Priors
Abstract
In this paper we focus on the estimation of the 3D Eu-clidean shape and motion of a non-rigid object which is moving rigidly while deforming and is observed by a per-spective camera. Our method exploits the fact that it is of-ten a reasonable assumption that some of the points are de-forming throughout the sequence while others remain rigid. First we use an automatic segmentation algorithm to iden-tify the set of rigid points which in turn is used to estimate the internal camera calibration parameters and the overall rigid motion. Finally we formalise the problem of non-rigid shape estimation as a constrained non-linear minimization adding priors on the degree of deformability of each point. We perform experiments on synthetic and real data which show firstly that even when using a minimal set of rigid points it is possible to obtain reliable metric information and secondly that the shape priors help to disambiguate the contribution to the image motion caused by the deformation and the perspective distortion. 1.
Cite
Text
Del Bue et al. "Non-Rigid Metric Shape and Motion Recovery from Uncalibrated Images Using Priors." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.209Markdown
[Del Bue et al. "Non-Rigid Metric Shape and Motion Recovery from Uncalibrated Images Using Priors." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/bue2006cvpr-non/) doi:10.1109/CVPR.2006.209BibTeX
@inproceedings{bue2006cvpr-non,
title = {{Non-Rigid Metric Shape and Motion Recovery from Uncalibrated Images Using Priors}},
author = {Del Bue, Alessio and Lladó, Xavier and Agapito, Lourdes},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2006},
pages = {1191-1198},
doi = {10.1109/CVPR.2006.209},
url = {https://mlanthology.org/cvpr/2006/bue2006cvpr-non/}
}