Color is a powerful visual cue for many computer vision
applications such as image segmentation and object recognition.
However, most of the existing color models depend on the i...
This paper presents a surface reconstruction algorithm that can recover correct shape geometry as well as its unknown topology from both volumetric images and unorganized point cl...
Ageometric framework for the recognition of three-dimensional objects represented by point
clouds is introducedin this paper. The proposed approach is based on comparing distribut...
We present a new approximate inference algorithm for Deep Boltzmann Machines (DBM's), a generative model with many layers of hidden variables. The algorithm learns a separate...
Abstract. In spite of over two decades of intense research, illumination and pose invariance remain prohibitively challenging aspects of face recognition for most practical applica...