RGB2Hands Benchmark
A Benchmark Dataset for Tracking Two Interacting Hands
J. Wang, F. Mueller, F. Bernard, S. Sorli, O. Sotnychenko, N. Qian, M. A. Otaduy, D. Casas, C. Theobalt
RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video
ACM Transactions on Graphics (TOG) (SIGGRAPH Asia 2020, Virtual Conference).
RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video
ACM Transactions on Graphics (TOG) (SIGGRAPH Asia 2020, Virtual Conference).
RGB2Hands is an RGB dataset for evaluating algorithms that tracks two hands during interactions. It consists of 4 sequences with varying types of hand-hand interactions. Hand joints locations were manually annotated on paired RGB and Depth images to provided 3D and 2D annotations. This dataset accompanies the SIGGRAPH Asia 2020 paper, RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video.
License
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
@article{wang_SIGAsia2020,
title={{RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video}},
author={Wang, Jiayi and Mueller, Franziska and Bernard, Florian and Sorli, Suzanne and Sotnychenko, Oleksandr and Qian, Neng and Otaduy, Miguel A. and Casas, Dan and Theobalt, Christian},
journal={ACM Transactions on Graphics (TOG)},
volume={39},
number={6},
year={2020},
month={12},
article={218},
publisher={ACM}
}
Downloads
- Compressed Zip: Single file (zip, 689 MB), SHA-256:
b5301b33aa7fdb6d4d4f727846cf75fe490f929fafd0a9563b894cc1b9ec5eb4
Data
- Color: Intel RealSense SR300 @640x480 px
- Depth: Intel RealSense SR300 @640x480 px
- Ground Truth: Manually annotated on depth data for 3D joint positions
- Camera Calibration: For mapping between world and camera coordinate systems (depth, color)