AtlasNet: A Papier-M\^ach\'e Approach to Learning 3D Surface Generation

TL;DR

AtlasNet is a novel 3D shape generation method that models surfaces as collections of parametric patches, offering improved accuracy, flexibility, and resolution independence over voxel or point cloud approaches.

Contribution

Introduces AtlasNet, a surface-based 3D shape generation framework that surpasses existing methods in precision, generalization, and arbitrary resolution output.

Findings

Outperforms baselines on ShapeNet for shape auto-encoding

Effective in single-view 3D reconstruction from images

Shows potential for morphing, parametrization, and super-resolution

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.