Highlight

ShapeNet: An Information-Rich 3D Model Repository

Presents ShapeNet, a large-scale, richly annotated repository of 3D CAD models organized under the WordNet taxonomy as a benchmark for graphics and vision.

Based on

ShapeNet: An Information-Rich 3D Model Repository

By Angel X. Chang, T. Funkhouser, L. Guibas et al.arXiv.org
Read original article →

ShapeNet is a richly annotated, large-scale repository of shapes represented by 3D CAD models of objects, drawn from many semantic categories and organized under the WordNet taxonomy. It is a collection of datasets that provides numerous semantic annotations for each 3D model, including consistent rigid alignments, parts, bilateral symmetry planes, physical sizes, and keywords, with further annotations planned. These annotations are exposed through a public web-based interface.

The interface enables visualization of object attributes, promotes data-driven geometric analysis, and provides a large-scale quantitative benchmark for research in computer graphics and vision. At the time of the technical report, ShapeNet had indexed more than 3,000,000 models, of which 220,000 were classified into 3,135 categories corresponding to WordNet synsets, giving the community a substantial shared resource for 3D shape understanding.

Abstract

ShapeNet is a large-scale, richly annotated repository of 3D shapes represented as CAD models spanning many semantic categories and organized under the WordNet taxonomy. Each model carries annotations such as rigid alignments, parts, bilateral symmetry planes, physical sizes, and keywords, exposed via a public web interface for visualization and data-driven geometric analysis. It is meant as a large-scale quantitative benchmark for graphics and vision research. At the report's time, ShapeNet indexed over 3,000,000 models, 220,000 of them classified into 3,135 categories.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

3D modelsCAD repositoryWordNet taxonomycomputer visioncomputer graphicsshape benchmark
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.