Rel3D

Rel3D is a large-scale dataset of human-annotated spatial relations in 3D. It consists of spatial relations situated in synthetic 3D scenes, making it possible to extract rich and accurate geometric and semantic information.

Data and Resources

Cite this as

Yutaro Yamada, Yingtian Tang, Ilker Yildirim (2024). Dataset: Rel3D. https://doi.org/10.57702/ecaj2yzm

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2012.01634
Citation
  • https://doi.org/10.48550/arXiv.2403.00729
Author Yutaro Yamada
More Authors
Yingtian Tang
Ilker Yildirim
Homepage https://github.com/nyu-dmlab/rel3d