Accurate Localization and Pose Estimation for Large 3D Models

Linus Svärm, Olof Enqvist, Magnus Oskarsson, Fredrik Kahl

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceedingPeer review


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.
Titel på värdpublikationComputer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on
FörlagIEEE - Institute of Electrical and Electronics Engineers Inc.
Antal sidor8
StatusPublished - 2014
EvenemangIEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), 2014 - Columbus, Ohio, USA
Varaktighet: 2014 juni 242014 juni 27


ISSN (tryckt)1063-6919


KonferensIEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), 2014
OrtColumbus, Ohio

Ämnesklassifikation (UKÄ)

  • Datorseende och robotik (autonoma system)
  • Matematik


Utforska forskningsämnen för ”Accurate Localization and Pose Estimation for Large 3D Models”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här