/temp

Primary LanguagePython

DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions



Demo | KoEBA

Requirements

  • CUDA 10.2
  • PyTorch 1.10.0
  • Python 3.7

Installation

You can install required environments using below commands:

git clone  https://github.com/deepbrainai-research/discohead
cd discohead
conda env create -n discohead python=3.7
conda activate discohead
conda install pytorch==1.10.0 torchvision==0.11.1 torchaudio==0.10.0 cudatoolkit=10.2 -c pytorch
pip install -r requirements.txt

Generating Demo Videos.

  • Download the pre-trained checkpoints from google drive and put into weight folder.
  • Download dataset.zip from google drive and unzip into dataset.
  • DisCoHead directory should have the following structure.
DisCoHead/
├── dataset/
│   ├── fig2/
│   ├── fig3/
│   ├── fig4/
├── weight/
│   ├── obama.pt
│   ├── grid.pt
│   ├── koeba.pt
├── modules/
‥‥
  • The --fig_number argument is used for specifying which figure you want to generate.
  • To reproduce fig. 2 of obama dataset, run command :
python test.py --fig_number 2

License

Non-commercial

Citation

To be updated