KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#developer-tools #dsh #dsh-plugin #ai-agent #claude-code #codex #typescript #ai-agents #mcp #cli #rust #deepseek-harness

Physics-Guided-Mocap

★ 37 Open GitHub ↗

The code for IJCAI 2023 paper "Physics-Guided Human Motion Capture with Pose Probability Modeling"

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# \[IJCAI2023\] Physics-Guided Human Motion Capture with Pose Probability Modeling

The code for IJCAI 2023 paper "Physics-Guided Human Motion Capture with Pose Probability Modeling" 
Jingyi Ju, [Buzhen Huang](http://www.buzhenhuang.com/), Chen Zhu, Zhihao Li, [Yangang Wang](https://www.yangangwang.com/#me) 
\[[Paper](https://www.ijcai.org/proceedings/2023/0105.pdf)\]

![figure](https://raw.githubusercontent.com/Me-Ditto/Physics-Guided-Mocap/master/images/pipeline.jpg)

## Installation
Create conda environment and install dependencies.
```
conda create -n Physics-Guided-Mocap python=3.8
conda install pytorch torchvision torchaudio pytorch-cuda=11.1 -c pytorch -c nvidia # install pytorch
pip install -r requirements.txt
```

1. Due to the licenses, please download SMPL model file [here](http://smplify.is.tuebingen.mpg.de/).
2. The [Mujoco](https://github.com/openai/mujoco-py/releases) environment is built into the project path(./mujoco_py) to avoid cumbersome environment configuration. We recommend to download [mujoco-py-1.50.1.0](https://github.com/openai/mujoco-py/releases/tag/1.50.1.0) and [mjpro150](https://www.roboti.us/download.html) and [activation key](https://www.roboti.us/license.html) for win10/win11.

Finally put these data following the directory structure as below:
```
${ROOT}
|-- assets
    |-- mujoco_models
    |-- bigfoot_template.pkl
    |-- bigfoot_template_v1.pkl
|-- data
    |-- mujoco
        |-- mujoco-py-1.50.1.0
        |-- mjpro150
        |-- mjkey.txt
    |-- sample_data
        |-- amass_copycat_occlusion.pkl
        |-- amass_copycat_take5_test_small.pkl
        |-- standing_neutral.pkl
    |-- smpl
        |-- SMPL_NEUTRAL.pkl
        |-- SMPL_FEMALE.pkl
        |-- SMPL_MALE.pkl
    |-- init_data.pkl
    |-- iter_19000.p
    |-- J_regressor_h36m.npy
    |-- J_regressor_halpe.npy
    |-- J_regressor_lsp.npy
```

## Usage

### Demo
- Reconstruct physically-plausible human motions with physics-guided diffusion framework.

```
python demo.py
```

### TODO:
* Release trained model
* Release training code

## Citation
If you find this code useful for your research, please consider citing the paper.
```
@inproceedings{ijcai2023p105,
  title     = {Physics-Guided Human Motion Capture with Pose Probability Modeling},
  author    = {Ju, Jingyi and Huang, Buzhen and Zhu, Chen and Li, Zhihao and Wang, Yangang},
  booktitle = {International Joint Conference on Artificial Intelligence, IJCAI},
  pages     = {947--955},
  year      = {2023},
}

```
## Reference
Some of the code is based on the following works. We gratefully appreciate the impact they have on our work.

[UniversalHumanoidControl](https://github.com/ZhengyiLuo/UniversalHumanoidControl) 
[SMPL-X](https://github.com/vchoutas/smplify-x) 
[CLIFF](https://github.com/huawei-noah/noah-research/tree/master/CLIFF)

Physics-Guided-Mocap

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README