Minimal Hand

A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.

This project provides the core components for hand motion capture:

estimating joint locations from a monocular RGB image (DetNet)
estimating joint rotations from locations (IKNet)

We focus on:

ease of use (all you need is a webcam)
time efficiency (on our 1080Ti, 8.9ms for DetNet, 0.9ms for IKNet)
robustness to occlusion, hand-object interaction, fast motion, changing scale and view point

Some links: [video] [paper] [supp doc] [webpage]

The release of training code is still in progress.

Usage

Install dependencies

Please check requirements.txt. All dependencies are available via pip and conda.

Prepare MANO hand model

Download MANO model from here and unzip it.
In config.py, set OFFICIAL_MANO_PATH to the left hand model.
Run python prepare_mano.py, you will get the converted MANO model that is compatible with this project at config.HAND_MESH_MODEL_PATH.

Prepare pre-trained network models

Download models from here.
Put detnet.ckpt.* in model/detnet, and iknet.ckpt.* in model/iknet.
Check config.py, make sure all required files are there.

Run the demo for webcam input

python app.py
Put your right hand in front of the camera. The pre-trained model is for left hand, but the input would be flipped internally.
Press ESC to quit.
Although the model is robust to variant scales, most ideally the image should be 1.3x larger than the hand boudning box. A good bounding box may result in better accuracy. You can track the bounding box with the 2D predictions of the model.

We found that the model may fail on some "simple" poses. We think this is because such poses were no presented in the training data. We are working on a v2 version with further extended data to tackle this problem.

Use the models in your project

Please check wrappers.py.

IKNet Alternative

We also provide an optimization-based IK solver here.

Dataset

The detection model is trained with following datasets:

The IK model is trained with the poses shipped with MANO.

Citation

This is the official implementation of the paper "Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data" (CVPR 2020).

The quantitative numbers reported in the paper can be found in plot.py.

If you find the project helpful, please consider citing us:

@inproceedings{zhou2020monocular,
  title={Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data},
  author={Zhou, Yuxiao and Habermann, Marc and Xu, Weipeng and Habibie, Ikhsanul and Theobalt, Christian and Xu, Feng},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={0--0},
  year={2020}
}

fweidner/minimal-hand