facebookresearch / AutoAvatar

AutoAvatar Autoregressive Neural Fields for Dynamic Avatar Modeling
Other
98 stars 9 forks source link

AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling

Ziqian Bai · Timur Bagautdinov · Javier Romero . Michael Zollhöfer · Ping Tan · Shunsuke Saito

ECCV 2022

Logo

AutoAvatar is an autoregressive approach for modeling dynamically deforming human bodies directly from raw scans without the need of precise surface registration.


Paper PDF Project Page video views

Data Preparation of DFaust

cd <workspace_folder>
mkdir DFaust
cd <workspace_folder>
git clone https://github.com/facebookresearch/AutoAvatar.git
    \<workspace_folder\>
    ├── DFaust
    │   ├── DFaust_67
    │   │   └── 50002
    │   │       └── *.npz
    │   └── scans
    │       └── 50002
    │           └── \<sequences_folders\>
    ├── SMPL
    │   ├── smplh
    │   │   ├── female
    │   │   ├── male
    │   │   └── neutral
    │   ├── dmpls
    │   │   ├── female
    │   │   ├── male
    │   │   └── neutral
    |   └── \<other_SMPL_related_files\>
    └── AutoAvatar

Environment Setup

cd AutoAvatar
conda create -n AutoAvatar python=3.8
conda activate AutoAvatar
bash setup.sh
mkdir external
cd external
git clone https://github.com/nghorbani/human_body_prior.git
cd human_body_prior
python setup.py develop

Data Preprocess

cd AutoAvatar
export PYTHONPATH=<workspace_folder>/AutoAvatar
python data/DFaust_generate.py --ws_dir <workspace_folder>

Train

cd AutoAvatar
export PYTHONPATH=<workspace_folder>/AutoAvatar
python exps/PosedDecKNN_dPoses_dHs/implicit_train_dfaust.py --ws_dir <workspace_folder> --configs_path configs/PosedDecKNN_dPoses_dHs/AutoRegr.yaml --configs_path_rollout configs/PosedDecKNN_dPoses_dHs/AutoRegr_Rollout2.yaml

Test

cd AutoAvatar
export PYTHONPATH=<workspace_folder>/AutoAvatar
python exps/PosedDecKNN_dPoses_dHs/implicit_eval_dfaust.py --ws_dir <workspace_folder> --ckpt_dir <checkpoint_folder>

Pretrained Model

Publication

If you find our code or paper useful, please consider citing:

@inproceedings{bai2022autoavatar,
  title={AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling},
  author={Bai, Ziqian and Bagautdinov, Timur and Romero, Javier and Zollh{\"o}fer, Michael and Tan, Ping and Saito, Shunsuke},
  booktitle={European conference on computer vision},
  year={2022},
}

License

CC-BY-NC 4.0. See the LICENSE file.