Date of Original Version
Abstract or Table of Contents
We address the problem of label assignment in computer vision: given a novel 3-D or 2-D scene, we wish to assign a unique label to every site (voxel, pixel, superpixel, etc.). To this end, the Markov Random Field framework has proven to be a model of choice as it uses contextual information to yield improved classiﬁcation results over locally indepen- dent classiﬁers. In this work we adapt a functional gradi- ent approach for learning high-dimensional parameters of random ﬁelds in order to perform discrete, multi-label clas- siﬁcation. With this approach we can learn robust models involving high-order interactions better than the previously used learning method. We validate the approach in the con- text of point cloud classiﬁcation and improve the state of the art. In addition, we successfully demonstrate the gener- ality of the approach on the challenging vision problem of recovering 3-D geometric surfaces from images.