This paper studies the problem of simultaneously aligning a batch of linearly correlated images despite gross corruption (such as occlusion). Our method seeks an optimal set of im...
Yigang Peng, Arvind Balasubramanian, John Wright, ...
Markerless tracking of human pose is a hard yet relevant problem. In this paper, we derive an efficient filtering algorithm for tracking human pose at 4-10 frames per second using...
Varun Ganapathi, Christian Plagemann, Sebastian Th...
Abstract. Tracking is usually interpreted as finding an object in single consecutive frames. Regularization is done by enforcing temporal smoothness of appearance, shape and motio...
Markus Unger, Thomas Mauthner, Thomas Pock, Horst ...
Simultaneous capture of the texture and shape of a moving object in real time is expected to be applicable to various fields including virtual reality and object recognition. Two...
Abstract— We describe a fast method to relocalise a monocular visual SLAM (Simultaneous Localisation and Mapping) system after tracking failure. The monocular SLAM system stores ...