ShapeNet is a large-scale, richly annotated repository of 3D CAD models, organized under the WordNet taxonomy. It aims to address the lack of large-scale, curated datasets for 3D models, which is a critical bottleneck in advancing data-driven methods in computer graphics and vision. ShapeNet contains over 3 million models, with 220,000 classified into 3,135 categories. The repository provides extensive annotations, including geometric attributes like rigid alignments, parts and symmetry planes, physical sizes, and keywords. These annotations are made available through a web-based interface for data visualization, geometric analysis, and benchmarking. The project is ongoing, with plans to expand the dataset, introduce additional annotation types, and integrate RGB-D data for more realistic representations. ShapeNet is expected to have a significant impact on research in computer graphics and vision, enabling data-driven methods and serving as a benchmark dataset.ShapeNet is a large-scale, richly annotated repository of 3D CAD models, organized under the WordNet taxonomy. It aims to address the lack of large-scale, curated datasets for 3D models, which is a critical bottleneck in advancing data-driven methods in computer graphics and vision. ShapeNet contains over 3 million models, with 220,000 classified into 3,135 categories. The repository provides extensive annotations, including geometric attributes like rigid alignments, parts and symmetry planes, physical sizes, and keywords. These annotations are made available through a web-based interface for data visualization, geometric analysis, and benchmarking. The project is ongoing, with plans to expand the dataset, introduce additional annotation types, and integrate RGB-D data for more realistic representations. ShapeNet is expected to have a significant impact on research in computer graphics and vision, enabling data-driven methods and serving as a benchmark dataset.