dc.contributor.author	Bronstein, Michael	en_US
dc.contributor.author	Kalogerakis, Evangelos	en_US
dc.contributor.author	Rodola, Emanuele	en_US
dc.contributor.author	Masci, Jonathan	en_US
dc.contributor.author	Boscaini, Davide	en_US
dc.contributor.editor	Augusto Sousa and Kadi Bouatouch	en_US
dc.date.accessioned	2016-04-26T08:14:04Z
dc.date.available	2016-04-26T08:14:04Z
dc.date.issued	2016	en_US
dc.description.abstract	The past decade in computer vision research has witnessed the re-emergence of deep learning, and in particular convolutional neural network (CNN) techniques, allowing to learn powerful image feature representations from large collections of examples. Nevertheless, when attempting to apply standard deep learning methods to geometric data which by its nature is non-Euclidean (e.g. 3D shapes, graphs), one has to face fundamental differences between images and geometric objects. The purpose of this tutorial is to overview the foundations and the state of the art on learning techniques for 3D shape analysis. Special focus will be put on deep learning (CNN) applied to Euclidean and non-Euclidean manifolds for tasks of shape classification, retrieval and correspondence. The tutorial will present in a new light the problems of shape analysis, emphasizing the analogies and differences with the classical 2D setting and showing how to adapt popular learning schemes to deal with deformable shapes.	en_US
dc.description.sectionheaders	Tutorials	en_US
dc.description.seriesinformation	EG 2016 - Tutorials	en_US
dc.identifier.doi	10.2312/egt.20161030	en_US
dc.identifier.issn	1017-4656	en_US
dc.identifier.uri	https://doi.org/10.2312/egt.20161030	en_US
dc.publisher	The Eurographics Association	en_US
dc.title	Deep Learning for Shape Analysis	en_US

Deep Learning for Shape Analysis

Files

Original bundle

Collections