Pose Estimation for Category Speci c Multiview Object Localization ∗ ¨

  • Ozuysal M
  • Lepetit V
  • Fua P
  • 50


    Mendeley users who have this article in their library.
  • N/A


    Citations of this article.


We propose an approach to overcome the two main challenges of 3D multiview object detection and localization: The variation of object features due to changes in the viewpoint and the variation in the size and aspect ratio of the object. Our approach proceeds in three steps. Given an initial bounding box of fixed size, we first refine its aspect ratio and size. We can then predict the viewing angle, under the hypothesis that the bounding box actually contains an object instance. Finally, a classifier tuned to this particular viewpoint checks the existence of an instance. As a result, we can find the object instances and estimate their poses, without having to search over all window sizes and potential orientations. We train and evaluate our method on a new object database specifically tailored for this task, containing realworld objects imaged over a wide range of smoothly varying viewpoints and significant lighting changes. We show that the successive estimations of the bounding box and the viewpoint lead to better localization results.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document


  • Mustafa Ozuysal

  • Vincent Lepetit

  • Pascal Fua

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free