https://arxiv.org/abs/1906.05856
Important Note from: https://peterwang512.github.io/FALdetector/
How to interpret the results
Welcome! Computer vision algorithms often work well on some images, but fail on others. Ours is like this too. We believe our work is a significant step forward in detecting and undoing facial warping by image editing tools. However, there are still many hard cases, and this is by no means a solved problem.
This is partly because our algorithm is trained on faces warped by the Face-aware Liquify tool in Photoshop, and will thus work well for these types of images, but not necessarily for others. We call this the "dataset bias" problem. Please see the paper for more details on this issue.
While we trained our models with various data augmentation to be more robust to downstream operations such as resizing, jpeg compression and saturation/brightness changes, there are many other retouches (e.g. airbrushing) that can alter the low-level statistics of the images to make the detection a really hard one.
from https://github.com/PeterWang512/FALdetector/blob/master/weights/download_weights.sh
wget https://www.dropbox.com/s/rb8zpvrbxbbutxc/global.pth?dl=0 -O ./weights/global.pth
wget https://www.dropbox.com/s/pby9dhpr6cqziyl/local.pth?dl=0 -O ./weights/local.pth
@inproceedings{wang2019detecting,
title={Detecting Photoshopped Faces by Scripting Photoshop},
author={Wang, Sheng-Yu and Wang, Oliver and Owens, Andrew and Zhang, Richard and Efros, Alexei A},
booktitle={ICCV},
year={2019}
}