Sciweavers

67 search results - page 2 / 14
» 3D Model based Object Class Detection in An Arbitrary View
Sort
View
BMVC
2010
13 years 3 months ago
Back to the Future: Learning Shape Models from 3D CAD Data
Recognizing 3D objects from arbitrary view points is one of the most fundamental problems in computer vision. A major challenge lies in the transition between the 3D geometry of o...
Michael Stark, Michael Goesele, Bernt Schiele
CVPR
2008
IEEE
14 years 7 months ago
Viewpoint-independent object class detection using 3D Feature Maps
This paper presents a 3D approach to multi-view object class detection. Most existing approaches recognize object classes for a particular viewpoint or combine classifiers for a f...
Joerg Liebelt, Cordelia Schmid, Klaus Schertler
AMFG
2003
IEEE
163views Biometrics» more  AMFG 2003»
13 years 10 months ago
Pose Estimation using 3D View-Based Eigenspaces
In this paper we present a method for estimating the absolute pose of a rigid object based on intensity and depth viewbased eigenspaces, built across multiple views of example obj...
Louis-Philippe Morency, Patrik Sundberg, Trevor Da...
CVPR
2007
IEEE
14 years 7 months ago
Flexible Object Models for Category-Level 3D Object Recognition
Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
Akash Kushal, Cordelia Schmid, Jean Ponce
3DOR
2010
13 years 14 days ago
Semantics-Driven Approach for Automatic Selection of Best Views of 3D Shapes
We introduce a new framework for the automatic selection of the best views of 3D models. The approach is based on the assumption that models belonging to the same class of shapes ...
Hamid Laga