Sciweavers

1871 search results - page 107 / 375
» Learning 3-D object orientation from images
Sort
View

Publication
241views
15 years 6 months ago
Fast and Automatic Object Pose Estimation for Range Images on the GPU
We present a pose estimation method for rigid objects from single range images. Using 3D models of the objects, many pose hypotheses are compared in a data-parallel version of t...
In Kyu Park, Marcel Germann, Michael D. Breitenste...
CVPR
2011
IEEE
14 years 10 months ago
Symmetric Piecewise Planar Object Reconstruction from a Single Image
Recovering 3D geometry from a single view of an object is an important and challenging problem in computer vision. Previous methods mainly focus on one specific class of objects ...
Tianfan XUE, Jianzhuang LIU
CVPR
2004
IEEE
16 years 8 months ago
View Independent Human Body Pose Estimation from a Single Perspective Image
Recovering the 3D coordinates of various joints of the human body from an image is a critical first step for several model-based human tracking and optical motion capture systems....
Vasu Parameswaran, Rama Chellappa
ECCV
2006
Springer
16 years 8 months ago
Real-Time Non-rigid Shape Recovery Via Active Appearance Models for Augmented Reality
One main challenge in Augmented Reality (AR) applications is to keep track of video objects with their movement, orientation, size, and position accurately. This poses a challengin...
Jianke Zhu, Steven C. H. Hoi, Michael R. Lyu
CVPR
2007
IEEE
16 years 8 months ago
Virtual Training for Multi-View Object Class Recognition
Our goal is to circumvent one of the roadblocks to using existing approaches for single-view recognition for achieving multi-view recognition, namely, the need for sufficient trai...
Han-Pang Chiu, Leslie Pack Kaelbling, Tomás...