zxz267 / AvatarJLM

[ICCV 2023] Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling

Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling

Xiaozheng Zheng^†  Zhuo Su^†  Chao Wen  Zhou Xue^*  Xiaojie Jin 

ByteDance

^†Equal contribution   ^*Corresponding author

🤩 Accepted to ICCV 2023

---

AvatarJLM uses tracking signals of the head and hands to estimate accurate, smooth, and plausible full-body motions.

📖 For more visual results, go checkout our project page

---

[Project Page] • [arXiv]

📣 Updates

[09/2023] Testing samples are available.

[09/2023] Training and testing codes are released.

[07/2023] AvatarJLM is accepted to ICCV 2023:partying_face:!

📁 Data Preparation

AMASS

1. Please download the datasets from AMASS.
2. Download the required body models and placed them in ./support_data/body_models directory of this repository. For the SMPL+H body model, download it from http://mano.is.tue.mpg.de/. Please download the AMASS version of the model with DMPL blendshapes. You can obtain dynamic shape blendshapes, e.g. DMPLs, from http://smpl.is.tue.mpg.de.
3. Run ./data/prepare_data.py to preprocess the input data for faster training. The data split for training and testing data under Protocol 1 in our paper is stored under the folder ./data/data_split (from AvatarPoser).

python ./data/prepare_data.py --protocol [1, 2, 3] --root [path to AMASS]

Real-Captured Data

1. Please download our real-captured testing data from Google Drive. The data is preprocessed to the same format as our preprocessed AMASS data.
2. Unzip the data and place it in ./data directory of this repository.

🖥️ Requirements

• Python >= 3.9
• PyTorch >= 1.11.0
• pyrender
• trimesh
• human_body_prior
• body_visualizer
• mesh

🚴 Training

python train.py --protocol [1, 2, 3] --task [name of the experiment] 

🏃‍♀️ Evaluation

python test.py --protocol [1, 2, 3, real] --task [name of the experiment] --checkpoint [path to trained checkpoint] [--vis]

🍭 Trained Model

Protocol	MPJRE	MPJPE	MPJVE	Trained Model
1	3.01	3.35	21.01	Google Drive
2-CMU-Test	5.36	7.28	26.46	Google Drive
2-BML-Test	4.65	6.22	34.45	Google Drive
2-MPI-Test	5.85	6.47	24.13	Google Drive
3	4.25	4.92	27.04	Google Drive

🤟 Citation

If you find our work useful for your research, please consider citing the paper:

@inproceedings{
  zheng2023realistic,
  title={Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling},
  author={Zheng, Xiaozheng and Zhuo Su and Wen, Chao and Xue, Zhou and Xiaojie Jin},
  booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
  year={2023}
}

🗞️ License

Distributed under the MIT License. See LICENSE for more information.

🙌 Acknowledgements

This project is built on source codes shared by AvatarPoser. We thank the authors for their great job!