Lipschitz Regularization of Images supported on Surfaces using Riemannian Morphological
Résumé
Dierent imaging modalities produce nowadays images on smooth surfaces, represented by images painted on meshes or point clouds. These Riemannian images are often nonsmooth and their regularization can be needed in many applications. This paper deals with the approxi-mation of a bounded nonsmooth image painted on a surface by a sequence of more regular functions, having in particular Lipschitz gradient, and without any hypothesis of dierentiability. We adopt here a geometric framework known as LasryLions regularization. The aim of the present contribution is to consider the extension of LasryLions regularization to Riemannian manifolds. We show that the key ingredients for such regularization are Riemannian morphological operators.
Domaines
Traitement des images [eess.IV]
Origine : Fichiers produits par l'(les) auteur(s)