AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxels

Paper | Project Page

Getting Started

• Create a conda environment conda env create -f environment.yaml
• Install Pytorch3d pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/py38_cu113_pyt1120/download.html
• Download our dataset Google drive and place it in this folder

Training

python train.py

During the training process, the intermediate results are saved in the results folder

Citation

@inproceedings{xu2023avatarmav,
  title={AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxels},
  author={Xu, Yuelang and Wang, Lizhen and Zhao, Xiaochen and Zhang, Hongwen and Liu, Yebin},
  booktitle={ACM SIGGRAPH 2023 Conference Proceedings},
  year={2023}
}