This repository contains source codes and training sets for the following paper:
"Iterative Facial Image Inpainting Based on an Encoder-Generator Architecture" by Yahya DOGAN and Hacer YALIM KELES.
The preprint version of the above paper is available at: https://arxiv.org/abs/2101.07036
- Spyder 4.2.x (recommended)
- Python 3.6
- Keras 2.2.4
- Tensorflow-gpu 1.13.1
- Clone this repo: git clone https://github.com/yahyadogan72/iterative_facial_image_inpainting.git
- Download CelebA dataset (note: convert delta files to png format), then put it in the following directory structure:
|-Iterative_facial_image_inpainting
|---Discriminator
|----dataset/real - Prepare the dataset for the discriminator network using the script.
- Train the discriminator network using the script.
- Download the pre-trained models and put them in the pretrained _models folder.
- Create dataset for the Unet model using the CRG model, then put it in the following directory structure:
|-Iterative_facial_image_inpainting
|--Unet
|---dataset
|----train/input - Train the Unet network using the script.
- Test the overall model using the script.
- You can use the script to create a mask that includes all facial landmarks in a face or download test data here.
If you find iterative facial image inpainting method useful in your research, please consider citing:
Dogan, Y. & Keles, H.Y. Neural Comput & Applic (2022). https://doi.org/10.1007/s00521-022-06987-y
@article{dogan2021iterative,
title={Iterative Facial Image Inpainting using Cyclic Reverse Generator},
author={Dogan, Yahya and Keles, Hacer Yalim},
journal={arXiv preprint arXiv:2101.07036},
year={2021}
}
yahyadogan72 at gmail.com