---
license: apache-2.0
---
## 🚀 Dataset Usage
To facilitate researchers, we provide the processed 272-dim Motion Representation of [BABEL](https://babel.is.tue.mpg.de/) dataset in this Hugging Face repo.

Motions are resampled into 30 FPS.

NOTE: ``t2m_babel_mean_std/`` contains the joint mean and std of both HumanML3D and BABEL dataset for joint training of the proposed [Causal TAE](https://github.com/zju3dv/MotionStreamer/blob/main/TRAIN_causal_TAE.sh).

❗️❗️❗️ The processed data is solely for academic purposes. Make sure you read through the [BABEL License](https://babel.is.tue.mpg.de/license.html).

## 📖 Paper & Project Page & Code
* [Arxiv Paper](https://arxiv.org/abs/2503.15451)
* [Project Page](https://zju3dv.github.io/MotionStreamer/)
* [Code](https://github.com/zju3dv/MotionStreamer)

## 🏃 Processing script
For more details of how to obtain the 272-dim motion representation, as well as other useful tools (e.g., Visualization and Conversion to BVH format), please refer to our [GitHub repo](https://github.com/Li-xingXiao/272-dim-Motion-Representation).

## 🌹 Acknowledgement
This repository builds upon the following awesome datasets and projects:
- [BABEL](https://babel.is.tue.mpg.de/)

## 🤝🏼 Citation
If our project is helpful for your research, please consider citing :
``` 
@article{xiao2025motionstreamer,
      title={MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space},
      author={Xiao, Lixing and Lu, Shunlin and Pi, Huaijin and Fan, Ke and Pan, Liang and Zhou, Yueer and Feng, Ziyong and Zhou, Xiaowei and Peng, Sida and Wang, Jingbo},
      journal={arXiv preprint arXiv:2503.15451},
      year={2025}
    }
```