https://github.com/albertpumarola/GANimation

GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch]
https://github.com/albertpumarola/GANimation

deep-learning eccv-2018 face-manipulation facial-expressions gan ganimation generative-adversarial-network pytorch

Last synced: 3 months ago
JSON representation

GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch]

• Host: GitHub
• URL: https://github.com/albertpumarola/GANimation
• Owner: albertpumarola
• License: gpl-3.0
• Created: 2018-07-23T16:39:34.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2019-12-23T06:27:57.000Z (about 5 years ago)
• Last Synced: 2024-08-04T06:03:53.127Z (6 months ago)
• Topics: deep-learning, eccv-2018, face-manipulation, facial-expressions, gan, ganimation, generative-adversarial-network, pytorch
• Language: Python
• Homepage: http://www.albertpumarola.com/research/GANimation/index.html
• Size: 75.2 KB
• Stars: 1,948
• Watchers: 76
• Forks: 413
• Open Issues: 43
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        


# GANimation: Anatomically-aware Facial Animation from a Single Image

### [[Project]](http://www.albertpumarola.com/research/GANimation/index.html)[ [Paper]](https://rdcu.be/bPuaJ) 

Official implementation of [GANimation](http://www.albertpumarola.com/research/GANimation/index.html). In this work we introduce a novel GAN conditioning scheme based on Action Units (AU) annotations, which describe in a continuous manifold the anatomical facial movements defining a human expression. Our approach permits controlling the magnitude of activation of each AU and combine several of them. For more information please refer to the [paper](https://arxiv.org/abs/1807.09251).

This code was made public to share our research for the benefit of the scientific community. Do NOT use it for immoral purposes.

![GANimation](http://www.albertpumarola.com/images/2018/GANimation/teaser.png)

## Prerequisites

- Install PyTorch (version 0.3.1), Torch Vision and dependencies from http://pytorch.org

- Install requirements.txt (```pip install -r requirements.txt```)

## Data Preparation

The code requires a directory containing the following files:

- `imgs/`: folder with all image

- `aus_openface.pkl`: dictionary containing the images action units.

- `train_ids.csv`: file containing the images names to be used to train.

- `test_ids.csv`: file containing the images names to be used to test.

An example of this directory is shown in `sample_dataset/`.

To generate the `aus_openface.pkl` extract each image Action Units with [OpenFace](https://github.com/TadasBaltrusaitis/OpenFace/wiki/Action-Units) and store each output in a csv file the same name as the image. Then run:

```

python data/prepare_au_annotations.py

```

## Run

To train:

```

bash launch/run_train.sh

```

To test:

```

python test --input_path path/to/img

```

## Citation

If you use this code or ideas from the paper for your research, please cite our paper:

```

@article{Pumarola_ijcv2019,

    title={GANimation: One-Shot Anatomically Consistent Facial Animation},

    author={A. Pumarola and A. Agudo and A.M. Martinez and A. Sanfeliu and F. Moreno-Noguer},

    booktitle={International Journal of Computer Vision (IJCV)},

    year={2019}

}

```