Recognizing 3D objects from arbitrary view points is one of the most fundamental problems in computer vision. A major challenge lies in the transition between the 3D geometry of o...
This paper describes a new technique for free-form object segmentation from a single arbitrary-viewed range image. The aim is to derive a surface description of objects that may va...
This paper describes a novel view-based learning algorithm for 3D object recognition from 2D images using a network of linear units. The SNoW learning architecture is a sparse netw...
We present a semi-automatic image-based modeling system to make 3-D models from photographs. The human operator intervenes only for simple and straightforward tasks. The design of...
This paper describes a head-tracking algorithm that is based on recognition and correlation-based weighted interpolation. The input is a sequence of 3D depth images generated by a...