Skip to content

official pytorch implementation of Animating-Through-Warping (MM 20 paper)

License

Notifications You must be signed in to change notification settings

duxingren14/ATW

Repository files navigation

Animating-Through-Warping

method

The official pytorch implementation of ATW paper, Animating Through Warping: an efficient Method for High-Quality Facial Expression Animation

Getting Started

Requirements

  • Python 3
  • PyTorch 0.4.1
  • visdom (optional, only for training with browser visualizer)
  • imageio (optional, only for generating GIF image in testing)

Installation

  • Clone this repo:
git clone ssh://[email protected]:2222/HiLens/hicam/facial_animation.git
cd facial_animation
conda create --name <env_name> --file requirements.txt

train

  • prepare the training datasets
  • uncomment the corresponding items in run.sh, then run the following command:
bash run.sh

test

  • download the pretrained models from google drive pretrained models
  • extract the file and put the folder pretrained_ckpt/ under ./ATW/
  • uncomment the corresponding items in the run.sh, then run the following command:
bash run.sh

Some Results

CelebA

celeba celeba

EmotionNet

emotionnet

RaFD

rafd

other

Feel free to contact me if you need any help from me related to this project.

About

official pytorch implementation of Animating-Through-Warping (MM 20 paper)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published