Skip to content

This repository contains a pytorch implementation of "MH-HMR: Human Mesh Recovery from Monocular Images via Multi-Hypothesis Learning".

Notifications You must be signed in to change notification settings

HaibiaoXuan/MH-HMR

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MH-HMR: Human Mesh Recovery from Monocular Images via Multi-Hypothesis Learning

Coming Soon

Image text


Dependencies

Requirements:

  • python3.6
  • pytorch==1.1.0
  • Pytorch
  • trimesh
  • open3d
  • ...

Install

conda create -n MHHMR python=3.6
conda install pytorch==1.7.0 torchvision==0.8.0 cudatoolkit=11.0 -c pytorch
or conda install pytorch==1.6.0 torchvision==0.7.0 cudatoolkit=10.2 -c pytorch
pip install -r requirements.txt

Demo

Training and Testing

Training

Testing

Citation

If you find this code useful, please cite our work with the following bibtex:

@article{xuan2023mhhmr,
  author = {Haibiao Xuan and Jinsong Zhang and Yu-Kun Lai and Kun Li},
  title = {MH-HMR: Human Mesh Recovery from Monocular Images via Multi-Hypothesis Learning},
  booktitle = {CAAI TRIT},
  year={2023}
}

Acknowledgement

License

About

This repository contains a pytorch implementation of "MH-HMR: Human Mesh Recovery from Monocular Images via Multi-Hypothesis Learning".

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published