Video Preprocessing

This repository provides tools for preprocessing videos for TaiChi, VoxCeleb and UvaNemo dataset used in paper.

Dowloading videos and cropping according to precomputed bounding boxes

1. Instal requirments:

pip install -r requirements.txt

2. Get the bounding boxes:

wget www.robots.ox.ac.uk/~vgg/data/voxceleb/data/vox2_dev_txt.zip
unzip vox2_dev_txt.zip

3. Run the script

python crop_vox.py --workers 40 --device_ids 0,1,2,3,4,5,6,7 --format .mp4 --dataset_version 2

Additional notes

Citation:

@InProceedings{Siarohin_2019_NeurIPS,
  author={Siarohin, Aliaksandr and Lathuilière, Stéphane and Tulyakov, Sergey and Ricci, Elisa and Sebe, Nicu},
  title={First Order Motion Model for Image Animation},
  booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
  month = {December},
  year = {2019}
}