We propose a multi-view pictorial structures model that builds on recent advances in 2D pose estimation and incorporates evidence across multiple viewpoints to allow for robust 3D pose estimation. We evaluate our multi-view pictorial structures approach on the HumanEva-I and MPII Cooking datasets. In comparison to related work for 3D pose estimation our approach achieves similar or better results while operating on single-frames only and not relying on activity specific motion models or tracking. Notably, our approach outperforms state-of-the-art for activities with more complex motions.
This site hosts the 2-camera version of the MPII (Max Planck Institute for Informatics) Cooking Activities pose challenge as well ground truth annotation for a several sequences from the HumanEva-I dataset used in .
Please contact us if you have questions.
The data is only to be used for scientific purposes and must not be republished other than by the Max Planck Institute for Informatics. The scientific use includes processing the data and showing it in publications and presentations. When using it please cite .
3D MPII Cooking pose challenge
- Data, ground truth, and evaluation code (1020 MB)
HumanEva-I ground truth
for the follwoing subject and sequences
- S1 - Walking, Jog, Box
- S2 - Walking, Jog
- S3 - Walking, Jog
- Ground truth annotations (4 MB)
The 3D MPII Cooking pose challenge data was recorded with a camera system from 4D View Solutions.
Feel free to subsribe to our mailing list to get updates (firstname.lastname@example.org).
Related datasets of our group
 Multi-View Pictorial Structures for 3D Human Pose Estimation, S. Amin, M. Andriluka, M. Rohrbach and B. Schiele, British Machine Vision Conference (BMVC), September, (2013)
 A Database for Fine Grained Activity Detection of Cooking Activities, M. Rohrbach, S. Amin, M. Andriluka and B. Schiele, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June, (2012)