This paper presents an approach to recover body motions from multiple views using a 3D skeletal model. It takes, as input, foreground silhouette sequences from multiple viewpoints...
We present a method for efficiently tracking objects represented as constellations of parts by integrating out the shape of the model. Parts-based models have been successfully ap...
We present a new method for multi-object segmentation in a maximum a posteriori estimation framework. Our method is motivated by the observation that neighboring or coupling objec...
Abstract. In this work, we present an approach to jointly segment a rigid object in a two-dimensional (2D) image and estimate its three-dimensional (3D) pose, using the knowledge o...
Samuel Dambreville, Romeil Sandhu, Anthony J. Yezz...
An automatic 3D model reconstruction technique is presented to acquire complete 3D models of real objects. The technique is based on novel approaches to pose estimation and integr...