Home

Awesome

FrankMocap: A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

FrankMocap pursues an easy-to-use single view 3D motion capture system developed by Facebook AI Research (FAIR). FrankMocap provides state-of-the-art 3D pose estimation outputs for body, hand, and body+hands in a single system. The core objective of FrankMocap is to democratize the 3D human pose estimation technology, enabling anyone (researchers, engineers, developers, artists, and others) can easily obtain 3D motion capture outputs from videos and images.

<b>Btw, why the name FrankMocap? </b> Our pipeline to integrate body and hand modules reminds us of Frankenstein's monster!

News:

Key Features

<p> <img src="https://github.com/jhugestar/jhugestar.github.io/blob/master/img/eft_bodymocap.gif" height="200"> </p> <p> <img src="https://github.com/jhugestar/jhugestar.github.io/blob/master/img/frankmocap_hand.gif" height="200"> </p> <p> <img src="https://github.com/jhugestar/jhugestar.github.io/blob/master/img/frankmotion_egohand.gif" height="150"> </p> <p> <img src="https://github.com/jhugestar/jhugestar.github.io/blob/master/img/frankmocap_wholebody.gif" height="200"> </p> <p> <img src="https://penincillin.github.io/project/frankmocap_iccvw2021/video_02.gif" height="200"> </p>

Installation

A Quick Start

Joint Order

Body Motion Capture Module

Hand Motion Capture Module

Whole Body Motion Capture Module (Body + Hand)

License

References

@InProceedings{rong2021frankmocap,
  title={FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration},
  author={Rong, Yu and Shiratori, Takaaki and Joo, Hanbyul},
  booktitle={IEEE International Conference on Computer Vision Workshops},
  year={2021}
}

@article{joo2020eft,
  title={Exemplar Fine-Tuning for 3D Human Pose Fitting Towards In-the-Wild 3D Human Pose Estimation},
  author={Joo, Hanbyul and Neverova, Natalia and Vedaldi, Andrea},
  journal={3DV},
  year={2021}
}