AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation

Résumé

We introduce a method for learning to generate the surface of 3D shapes. Our approach represents a 3D shape as a collection of parametric surface elements and, in contrast to methods generating voxel grids or point clouds, naturally infers a surface representation of the shape. Beyond its novelty, our new shape generation framework, AtlasNet, comes with significant advantages, such as improved precision and generalization capabilities, and the possibility to generate a shape of arbitrary resolution without memory issues. We demonstrate these benefits and compare to strong baselines on the ShapeNet benchmark for two applications: (i) auto-encoding shapes, and (ii) single-view reconstruction from a still image. We also provide results showing its potential for other applications, such as morphing, parametrization, super-resolution, matching, and co-segmentation.
Fichier principal
Vignette du fichier
1802.05384.pdf (4.45 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01718933 , version 1 (27-02-2018)

Identifiants

Citer

Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan Russell, Mathieu Aubry. AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation. CVPR 2018, Jun 2018, Salt Lake City, United States. ⟨hal-01718933⟩
829 Consultations
1465 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More