Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Accurate Localization and Pose Estimation for Large 3D Models

Svärm, Linus LU ; Enqvist, Olof ; Oskarsson, Magnus LU orcid and Kahl, Fredrik LU (2014) IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), 2014 p.532-539
Abstract
We consider the problem of localizing a novel image in a large 3D model. In principle, this is just an instance of camera pose estimation, but the scale introduces some challenging problems. For one, it makes the correspondence problem very difficult and it is likely that there will be a significant rate of outliers to handle. In this paper we use recent theoretical as well as technical advances to tackle these problems. Many modern cameras and phones have gravitational sensors that allow us to reduce the search space. Further, there are new techniques to efficiently and reliably deal with extreme rates of outliers. We extend these methods to camera pose estimation by using accurate approximations and fast polynomial solvers. Experimental... (More)
We consider the problem of localizing a novel image in a large 3D model. In principle, this is just an instance of camera pose estimation, but the scale introduces some challenging problems. For one, it makes the correspondence problem very difficult and it is likely that there will be a significant rate of outliers to handle. In this paper we use recent theoretical as well as technical advances to tackle these problems. Many modern cameras and phones have gravitational sensors that allow us to reduce the search space. Further, there are new techniques to efficiently and reliably deal with extreme rates of outliers. We extend these methods to camera pose estimation by using accurate approximations and fast polynomial solvers. Experimental results are given demonstrating that it is possible to reliably estimate the camera pose despite more than 99% of outlier correspondences. (Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Localization Optimization Polynomial solvers Pose Estimation
host publication
Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on
pages
8 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), 2014
conference location
Columbus, Ohio, United States
conference dates
2014-06-24 - 2014-06-27
external identifiers
  • wos:000361555600068
  • scopus:84911381857
ISSN
1063-6919
DOI
10.1109/CVPR.2014.75
language
English
LU publication?
yes
id
66323703-10d2-4193-bf47-9e4c54f3ce54 (old id 5052468)
date added to LUP
2016-04-01 13:04:31
date last changed
2021-09-29 01:12:38
@inproceedings{66323703-10d2-4193-bf47-9e4c54f3ce54,
  abstract     = {We consider the problem of localizing a novel image in a large 3D model. In principle, this is just an instance of camera pose estimation, but the scale introduces some challenging problems. For one, it makes the correspondence problem very difficult and it is likely that there will be a significant rate of outliers to handle. In this paper we use recent theoretical as well as technical advances to tackle these problems. Many modern cameras and phones have gravitational sensors that allow us to reduce the search space. Further, there are new techniques to efficiently and reliably deal with extreme rates of outliers. We extend these methods to camera pose estimation by using accurate approximations and fast polynomial solvers. Experimental results are given demonstrating that it is possible to reliably estimate the camera pose despite more than 99% of outlier correspondences.},
  author       = {Svärm, Linus and Enqvist, Olof and Oskarsson, Magnus and Kahl, Fredrik},
  booktitle    = {Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on},
  issn         = {1063-6919},
  language     = {eng},
  pages        = {532--539},
  publisher    = {IEEE - Institute of Electrical and Electronics Engineers Inc.},
  title        = {Accurate Localization and Pose Estimation for Large 3D Models},
  url          = {http://dx.doi.org/10.1109/CVPR.2014.75},
  doi          = {10.1109/CVPR.2014.75},
  year         = {2014},
}