Using GANs to Synthesise Minimum Training Data for Deepfake Generation

TL;DR

This paper demonstrates that GANs can generate diverse synthetic images from limited data, enabling the creation of high-quality deepfake videos with fewer training images than traditionally required.

Contribution

The study introduces a method using GAN-generated facial images with expression variability to produce realistic deepfakes from minimal training data.

Findings

GANs can produce diverse facial images from small datasets

Synthetic images improve deepfake quality with fewer training samples

Near-realistic deepfakes are achievable with limited data

Abstract

There are many applications of Generative Adversarial Networks (GANs) in fields like computer vision, natural language processing, speech synthesis, and more. Undoubtedly the most notable results have been in the area of image synthesis and in particular in the generation of deepfake videos. While deepfakes have received much negative media coverage, they can be a useful technology in applications like entertainment, customer relations, or even assistive care. One problem with generating deepfakes is the requirement for a lot of image training data of the subject which is not an issue if the subject is a celebrity for whom many images already exist. If there are only a small number of training images then the quality of the deepfake will be poor. Some media reports have indicated that a good deepfake can be produced with as few as 500 images but in practice, quality deepfakes require many thousands of images, one of the reasons why deepfakes of celebrities and politicians have become so popular. In this study, we exploit the property of a GAN to produce images of an individual with variable facial expressions which we then use to generate a deepfake. We observe that with such variability in facial expressions of synthetic GAN-generated training images and a reduced quantity of them, we can produce a near-realistic deepfake videos.