Many methods for 3D reconstruction in computer vision rely on probability models, for example, Bayesian reasoning. Here we introduce a probability model of surface visibilities in ...
Abstract. We propose a new approach to the correspondence problem that makes use of non-parametric local transforms as the basis for correlation. Non-parametric local transforms re...
We propose an approach for non-rigid tracking that represents objects by their set of distribution parameters. Compared to joint histogram representations, a set of parameters suc...
This paper deals with edge detection and vertex characterization of 3D meshes. First, a new measure is introduced, the saliency degree, which provide directly the shape informatio...
Nicolas Walter, Olivier Aubreton, Olivier Laligant
In this paper, We propose an efficient compression method to encode the geometry of 3D mesh sequences of objects sharing the same connectivity. Our approach is based on the cluste...