3D Poses in the Wild Dataset

Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera

Timo von Marcard1, Roberto Henschel1, Michael Black2, Bodo Rosenhahn2 and Gerard Pons-Moll3

1TNT, Leibniz University of Hannover 
2Max Planck Institute for Intelligent Systems
3Max Planck Institute for Informatics, Saarland Informatics Campus

ECCV 2018 Munich, Germany



The "3D Poses in the Wild dataset" is the first dataset in the wild with accurate 3D poses for evaluation. While other datasets outdoors exist, they are all restricted to a small recording volume. 3DPW is the first one that includes video footage taken from a moving phone camera.

The dataset includes:


We provide 6 sample sequences of the dataset. Full dataset will be available soon! To download, you have to first read and agree the license terms:

  • License

  • Requirements

    To run the example scripts, you will need the following:
  • Numpy & Scipy
  • Chumpy
  • OpenCV (2)
  • OpenDR
  • SMPL

  • Citation

    If you use this dataset, you agree to cite the corresponding ECCV'18 paper:
        title = {Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera},
        author = {von Marcard, Timo and Henschel, Roberto and Black, Michael and Rosenhahn, Bodo and Pons-Moll, Gerard},
        booktitle = {European Conference on Computer Vision (ECCV)},
        year = {2018},
        month = {sep}