HybrIK

This repo contains the code of our paper:

HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation

Jiefeng Li, Chao Xu, Zhicun Chen, Siyuan Bian, Lixin Yang, Cewu Lu

[arXiv] [Project Page]

In CVPR 2021

Twist-and-Swing Decomposition

TODO

Provide pretrained model
Provide parsed data annotations

Installation instructions

# 1. Create a conda virtual environment.
conda create -n hybrik python=3.6 -y
conda activate hybrik

# 2. Install PyTorch
conda install pytorch==1.1.0 torchvision==0.3.0

# 3. Pull our code
git clone https://github.com/Jeff-sjtu/HybrIK.git
cd HybrIK

# 4. Install
python setup.py develop

Download models

Download the SMPL model basicModel_neutral_lbs_10_207_0_v1.0.0.pkl from here at common/utils/smplpytorch/smplpytorch/native/models.
Download our pretrained model from [ Google Drive | Baidu ].

Fetch data

Download Human3.6M, MPI-INF-3DHP, 3DPW and MSCOCO datasets. You need to follow directory structure of the data as below.

|-- data
`-- |-- h36m
    `-- |-- annotations
        `-- images
`-- |-- pw3d
    `-- |-- json
        `-- imageFiles
`-- |-- 3dhp
    `-- |-- annotation_mpi_inf_3dhp_train.json
        |-- annotation_mpi_inf_3dhp_test.json
        |-- mpi_inf_3dhp_train_set
        `-- mpi_inf_3dhp_test_set
`-- |-- coco
    `-- |-- annotations
        |   |-- person_keypoints_train2017.json
        |   `-- person_keypoints_val2017.json
        |-- train2017
        `-- val2017

Download Human3.6M parsed annotations. [ Google | Baidu ]
Download 3DPW parsed annotations. [ Google | Baidu ]
Download MPI-INF-3DHP parsed annotations. [ Google | Baidu ]

Train from scratch

./scripts/train_smpl.sh train_res34 ./configs/256x192_adam_lr1e-3-res34_smpl_3d_base_2x_mix.yaml

Evaluation

Download the pretrained model [Google Drive].

./scripts/validate_smpl.sh ./configs/256x192_adam_lr1e-3-res34_smpl_24_3d_base_2x_mix.yaml ./pretrained_res34.pth

Citing

If our code helps your research, please consider citing the following paper:

@inproceedings{li2020hybrik,
    title={HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation},
    author={Li, Jiefeng and Xu, Chao and Chen, Zhicun and Bian, Siyuan and Yang, Lixin and Lu, Cewu},
    booktitle={CVPR},
    year={2021}
}

wangzheallen/HybrIK