GazeAnimation - Official Tensorflow Implementation

0

26

28

3

4

5

Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild

Jichao Zhang, Jingjing Chen, Hao Tang, Wei Wang, Yan Yan, Enver Sangineto, Nicu Sebe

In ACM MM 2020.

Paper: https://arxiv.org/abs/2008.03834

Citation

@inproceedings{zhangGazeAnimation,
  title={Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild},
  author={Jichao Zhang, Jingjing Chen, Hao Tang, Wei Wang, Yan Yan, Enver Sangineto, Nicu Sebe},
  booktitle={ACM MM},
  year={2020}
}

Network Architecture

model

Dependencies

Python=3.6
pip install -r requirements.txt

Or Using Conda

-conda create -name GazeA python=3.6
-conda install tensorflow-gpu=1.9

Other packages installed by pip.

Usage

  • Clone this repo:
git clone https://github.com/zhangqianhui/GazeAnimation.git
cd GazeAnimation

  • Download the CelebAGaze dataset

    Download the tar of CelebAGaze dataset from Google Driver Linking.

    cd your_path
    tar -xvf CelebAGaze.tar
    

    Please edit the options.py and change your dataset path

  • VGG-16 pretrained weights

wget http://download.tensorflow.org/models/vgg_16_2016_08_28.tar.gz .
tar -xvf vgg_16_2016_08_28.tar.gz

Please edit the options.py and change your vgg path

  • Train the model using command line with python
python train.py --use_sp --gpu_id='0' --exper_name='log8_7' --crop_w=50 --crop_h=30
  • Test the model
python test.py --exper_name='log8_7' --gpu_id='0' --crop_h=30 --crop_w=50 --test_sample_dir='test_sample_dir' --checkpoints='checkpoints'

Or Using scripts for training

bash scripts/train_log8_7.sh

Using scripts for testing and pretained model can be downloaded Pretrained Model

bash scripts/test_log8_7.sh

Experiment Result

Gaze Correction

correction

Gaze Animation

9

10

12

13

14

16

18

19

23