amonszpart / Lifting-from-the-Deep-release

Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"

Lifting from the Deep

Denis Tome', Chris Russell, Lourdes Agapito

Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image, CVPR 2017

This project is licensed under the terms of the GNU GPLv3 license. By using the software, you are agreeing to the terms of the license agreement (link).

Dependencies

The code is compatible with python2.7

• Tensorflow 1.0
• OpenCV

Models

The architecture extends the one proposed in Convolutional Pose Machines (CPM).

For this demo, CPM's caffe-models trained on the MPI datasets (link) are used for 2D pose estimation, whereas for 3D pose estimation our probabilistic 3D pose model is trained on the Human3.6M dataset.

Testing

• First, run setup.sh to retreive the trained models and to install the external utilities.
• Run demo.py to evaluate the test image.

Additional material

• Project webpage
• Some videos.

Citation

@article{tome2017lifting,
    title={Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image},
    author={Tome, Denis and Russell, Chris and Agapito, Lourdes},
    journal={arXiv preprint arXiv:1701.00295},
    year={2017}
}

Notes

The models provided for the demo are NOT the ones that have been used to generate results for the paper. We are still in the process of converting all the code.