This paper describes methods for recovering time-varying shape and motion of nonrigid 3D objects from uncalibrated 2D point tracks. For example, given a video recording of a talkin...
Lorenzo Torresani, Aaron Hertzmann, Christoph Breg...
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
Boxes are the universal choice for packing, storage, and transportation. In this paper we propose a template-based algorithm for recognition of box-like objects, which is invarian...
Abstract. This paper presents the integration of 3D shape knowledge into a variational model for level set based image segmentation and tracking. Having a 3D surface model of an ob...
A general framework simultaneously addressing pose
estimation, 2D segmentation, object recognition, and 3D
reconstruction from a single image is introduced in this
paper. The pr...