Practically all existing approaches to structure and motion computation use only positive image correspondences to verify the camera pose hypotheses. Incorrect epipolar geometries...
Learning Bayesian networks from data is an N-P hard problem with important practical applications. Several researchers have designed algorithms to overcome the computational comple...
This paper presents a framework for finding point correspondences in monocular image sequences over multiple frames. The general problem of multi-frame point correspondence is NP ...
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...
This paper addresses the general 3-D rigid motion problem, where the point correspondences and the motion parameters between two sets of 3-D points are to be recovered. The existe...
Xiaoguang Wang, Yong-Qing Cheng, Robert T. Collins...