This is the official implementation of HaWoR, a hand reconstruction model in the world coordinates:

git clone --recursive https://github.com/ThunderVVV/HaWoR.git
cd HaWoR

The code has been tested with PyTorch 1.13 and CUDA 11.7. Higher torch and cuda versions should be also compatible. It is suggested to use an anaconda environment to install the the required dependencies:

conda create --name hawor python=3.10
conda activate hawor

pip install torch==1.13.0+cu117 torchvision==0.14.0+cu117 --extra-index-url https://download.pytorch.org/whl/cu117
# Install requirements
pip install -r requirements.txt
pip install pytorch-lightning==2.2.4 --no-deps
pip install lightning-utilities torchmetrics==1.4.0

cd thirdparty/DROID-SLAM
python setup.py install

Download DROID-SLAM official weights droid.pth, put it under ./weights/external/.

Download Metric3D official weights metric_depth_vit_large_800k.pth, put it under thirdparty/Metric3D/weights.

wget https://huggingface.co/spaces/rolpotamias/WiLoR/resolve/main/pretrained_models/detector.pt -P ./weights/external/
wget https://huggingface.co/ThunderVVV/HaWoR/resolve/main/hawor/checkpoints/hawor.ckpt -P ./weights/hawor/checkpoints/
wget https://huggingface.co/ThunderVVV/HaWoR/resolve/main/hawor/checkpoints/infiller.pt -P ./weights/hawor/checkpoints/
wget https://huggingface.co/ThunderVVV/HaWoR/resolve/main/hawor/model_config.yaml -P ./weights/hawor/

It is also required to download MANO model from MANO website. Create an account by clicking Sign Up and download the models (mano_v*_*.zip). Unzip and put the hand model to the _DATA/data/mano/MANO_RIGHT.pkl and _DATA/data_left/mano_left/MANO_LEFT.pkl.

Note that MANO model falls under the MANO license.

For visualizaiton in world view, run with:

python demo.py --video_path ./example/video_0.mp4  --vis_mode world

For visualizaiton in camera view, run with:

python demo.py --video_path ./example/video_0.mp4 --vis_mode cam

The training code will be released soon.

Parts of the code are taken or adapted from the following repos:

• HaMeR
• WiLoR
• SLAHMR
• TRAM
• CMIB

HaWoR models fall under the CC-BY-NC--ND License. This repository depends also on MANO Model, which are fall under their own licenses. By using this repository, you must also comply with the terms of these external licenses.

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

@article{zhang2025hawor,
      title={HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos},
      author={Zhang, Jinglei and Deng, Jiankang and Ma, Chao and Potamias, Rolandos Alexandros},
      journal={arXiv preprint arXiv:2501.02973},
      year={2025}
    }