This is the PyTorch implementation of our BMVC 2021 paper AniFormer: Data-driven 3D Animation with Transformer. Haoyu Chen, Hao Tang, Nicu Sebe, Guoying Zhao.

If you use our code or paper, please consider citing:

@inproceedings{chen2021AniFormer,
  title={AniFormer: Data-driven 3D Animation withTransformer},
  author={Chen, Haoyu and Tang, Hao and Sebe, Nicu and Zhao, Guoying},
  booktitle={BMVC},
  year={2021}
}

Requirements:

• python3.6
• numpy
• pytorch==1.1.0 and above
• trimesh

Please download DFAUST dataset from DFAUST link for training the model.

Generate the driving sequence based on our script:

TBD

The usage of our code is easy, just run the code below.

python train.py

Part of our code is based on

3D transfer: NPT，

Transformer framework: (https://github.com/lucidrains/vit-pytorch)

Many thanks!

MIT-2.0 License