Geodesy

Quantum mechanics

Algorithm

Benchmark (surveying)

Statistics

Computer science

Parametric surface

Radiative transfer

Surface (topology)

Physics

Voxel

Segmentation

Point cloud

Pattern recognition (psychology)

Parametrization (atmospheric modeling)

Mathematics

Politics

Geography

Political science

Surface reconstruction

Mathematical analysis

Artificial intelligence

Geometry

Representation (politics)

Morphing

Parametric statistics

Matching (statistics)

Point (geometry)

Generalization

Computer vision

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) autoencoding 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.

A Papier-Mache Approach to Learning 3D Surface Generation