In this paper, parallelepipeds and their use in camera calibration and 3D reconstruction processes are studied. Parallelepipeds naturally characterize rigidity constraints present...
Abstract. Volumetric structures are frequently used as shape descriptors for 3D data. The capture of such data is being facilitated by developments in multi-view video and range sc...
Gabriel J. Brostow, Irfan A. Essa, Drew Steedly, V...
Given a set of images of scenes containing multiple object categories (e.g. grass, roads, buildings) our objective is to discover these objects in each image in an unsupervised man...
Abstract. In this paper, we introduce background cut, a high quality and realtime foreground layer extraction algorithm. From a single video sequence with a moving foreground objec...
Summarizing the contents of a video containing human activities is an important problem in computer vision and has important applications in automated surveillance systems. Summar...