MOYO

MOYO 🧘🏻‍♀️: A dataset containing complex yoga poses, multi-view videos, SMPL-X meshes, pressure and body center of mass

The MOYO Dataset contains 200 highly complex poses captured using a synchronized Mocap system, pressure mat, and a multi-view RGB video system with 8 static, calibrated cameras. The dataset contains ∼1.75M RGB frames in 4K resolution paired with ground-truth SMPL-X fits, pressure measurements, and body center of mass. Compared to the existing datasets, MoYo is more challenging: it has extreme out-of-domain poses, strong self-occlusion, and significant body-ground and self-contact.

The MoYo Dataset contains

moyo_offer-crop

Referencing MOYO

@inproceedings{tripathi2023ipman,
    title = {{3D} Human Pose Estimation via Intuitive Physics},
    author = {Tripathi, Shashank and M{\"u}ller, Lea and Huang, Chun-Hao P. and Taheri Omid and Black, Michael J. and Tzionas, Dimitrios},
    booktitle = {Conference on Computer Vision and Pattern Recognition ({CVPR})},
    pages = {4713--4725},
    year = {2023},
    url = {https://ipman.is.tue.mpg.de}
}