GANerated Hands Dataset

An Enhanced Dataset for RGB Hand Pose Estimation With Full 3D Annotation

F. Mueller, F. Bernard, O. Sotnychenko, D. Mehta, S. Sridhar, D. Casas, C. Theobalt
GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB
Computer Vision and Pattern Recognition (CVPR) 2018, Salt Lake City, Utah, USA.

This dataset accompanies the CVPR 2018 paper, GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB. The dataset contains more than 330,000 color images of hands with 2D and 3D annotation for 21 keypoints of the hand. The images were initially synthetically generated and afterwards fed to a GAN for image-to-image translation to make the features more similar to real hands. A geometric consistency constraint during translation ensures that the perfect and inexpensive annotations of the synthetic hands can be transferred to the enhanced GANerated images.


This dataset can only be used for scientific/non-commercial purposes. Please refer to the detailed license which is also enclosed in the download file. If you use this dataset, you are required to cite the following paper. BibTeX, 1 KB

 author = {Mueller, Franziska and Bernard, Florian and Sotnychenko, Oleksandr and Mehta, Dushyant and Sridhar, Srinath and Casas, Dan and Theobalt, Christian},
 title = {GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB},
 booktitle = {Proceedings of Computer Vision and Pattern Recognition ({CVPR})},
 url = {},
 numpages = {11},
 month = {June},
 year = {2018}


  • Compressed Zip: Single file (zip, 35.95 GB), SHA-256:
  • Browse: here


  • Color: resolution 256x256 px
  • Ground Truth: 2D and 3D positions of all 21 hand keypoints


  • June 28, 2018 - v2: Corrected 3D annotations and added 2D annotations.


Franziska Mueller

Back to CVPR 2018

Page last updated June-2018.

Imprint/Impressum | Data Protection/Datenschutzhinweis