Spaces and manifolds of shapes in computer vision: An overview

摘要

We provide an overview of several shape space models that have been proposed in the past few years, focusing, in particular on models involving Riemannian manifolds of shapes. The discussion is organized in three stages, starting with a review of some shape representation methods, followed by shape space structures, from metric spaces to manifolds, and concluding with a short description of some of the applications that resulted from such models.