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...
— The problem of accurate 6-DoF pose estimation of 3D objects based on their shape has so far been solved only for specific object geometries. Edge-based recognition and trackin...
3D parametric deformable models have been used to extract volumetric object boundaries and they generate smooth boundary surfaces as results. However, in some segmentation cases, ...
Tian Shen, Xiaolei Huang, Hongsheng Li, Edward Kim...
This paper presents a surface reconstruction algorithm that can recover correct shape geometry as well as its unknown topology from both volumetric images and unorganized point cl...
This paper presents a new approach to scene analysis, which aims at extracting structured information from a video sequence using directly low-level data. The method models the se...