This repo is the official implementation of "MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation, Wenhao Li, Hong Liu, Hao Tang, Pichao Wang, Luc Van Gool" in PyTorch.
- Cuda 11.1
- Python 3.6
- Pytorch 1.7.1
Please download the dataset from Human3.6m website and refer to VideoPose3D to set up the Human3.6M dataset ('./dataset' directory).
${POSE_ROOT}/
|-- dataset
| |-- data_3d_h36m.npz
| |-- data_2d_h36m_cpn_ft_h36m_dbb.npz
The pretrained model can be found in Google_Drive, please download it and put in the './checkpoint' dictory.
To test on pretrained model on Human3.6M:
python main.py --reload --previous_dir 'checkpoint/pretrained'
Here, we compare our MHFormer with recent state-of-the-art methods on Human3.6M dataset. Evaluation metric is Mean Per Joint Position Error (MPJPE) in mm​.
Models | MPJPE |
---|---|
VideoPose3D | 46.8 |
PoseFormer | 44.3 |
MHFormer | 43.0 |
To train on Human3.6M:
python main.py --train
If you find our work useful in your research, please consider citing:
@article{li2021mhformer,
title={MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation},
author={Li, Wenhao and Liu, Hong and Tang, Hao and Wang, Pichao and Van Gool, Luc},
journal={arXiv preprint arXiv:2111.12707},
year={2021}
}
Our code is extended from the following repositories. We thank the authors for releasing the codes.