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

Abstract : 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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [30 references]  Display  Hide  Download

https://hal.inria.fr/hal-01718933
Contributor : Thibault Groueix <>
Submitted on : Tuesday, February 27, 2018 - 6:05:23 PM
Last modification on : Tuesday, March 5, 2019 - 2:40:07 PM
Document(s) archivé(s) le : Monday, May 28, 2018 - 5:48:05 PM

File

1802.05384.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01718933, version 1
  • ARXIV : 1802.05384

Citation

Thibault Groueix, Matthew Fisher, Vladimir 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⟩

Share

Metrics

Record views

415

Files downloads

612