In this paper we propose a new method for the simultaneous segmentation and 3D reconstruction of interest point based articulated motion. We decompose a set of point tracks into r...
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...
We present a recognition-driven navigation system for large-scale 3D virtual environments. The proposed system contains three parts, virtual environment reconstruction, feature da...
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...
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...