MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

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.

Dependencies

• Cuda 11.1
• Python 3.6
• Pytorch 1.7.1

Dataset setup

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

Download pretrained model

The pretrained model can be found in Google_Drive, please download it and put in the './checkpoint' dictory.

Test the model

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​.

Train the model

To train on Human3.6M:

python main.py --train

Citation

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},
  year={2021}
}

Acknowledgement

Our code is extended from the following repositories. We thank the authors for releasing the codes.

• 3d-pose-baseline
• 3d_pose_baseline_pytorch
• VideoPose3D
• ST-GCN
• StridedTransformer-Pose3D