PartNet

The PartNet dataset is a large-scale benchmark for 3D object recognition and retrieval. It consists of 527 objects composed of 2690 parts, which can be composited into a generated object through retrieval.

Data and Resources

Cite this as

K. Mo, S. Zhu, A. X. Chang, L. Yi, S. Tripathi, L. J. Guibas, H. Su (2024). Dataset: PartNet. https://doi.org/10.57702/rd3nrble

DOI retrieved: November 25, 2024

Additional Info

Field Value
Created November 25, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.1811.10837
Citation
  • https://doi.org/10.48550/arXiv.2404.19639
  • https://doi.org/10.48550/arXiv.2405.05876
  • https://doi.org/10.48550/arXiv.1912.00145
  • https://doi.org/10.48550/arXiv.2312.09570
Author K. Mo
More Authors
S. Zhu
A. X. Chang
L. Yi
S. Tripathi
L. J. Guibas
H. Su
Homepage https://www.robots.ox.ac.uk/~vgg/data/pn.html