Pictorial Structures (PS) define a probabilistic model of 2D articulated objects in images. Typical PS models assume an object can be represented by a set of rigid parts connecte...
Marker-less motion capture is a challenging problem, particularly when only monocular video is available. We estimate human motion from monocular video by recovering three-dimensi...
Marek Vondrak, Leonid Sigal, Jessica K. Hodgins, O...
This paper presents an approach for including 3D prior models into a factorization framework for structure from motion. The proposed method computes a closed-form affine fit which...
Camera calibration methods, whether implicit or explicit, are a critical part of most 3D vision systems. These methods involve estimation of a model for the camera that produced t...
Nearly every structured prediction problem in computer vision requires approximate inference due to large and complex dependencies among output labels. While graphical models prov...