Use of Generative Adversarial Networks for the creation and manipulation of facial images in the context of studying false memories and its effects on wrongful conviction cases

While GAN images became more realistic over time, one of their main challenges is controlling their output, i.e. changing specific features such as pose, face shape and hair style in an image of a face. Style-Based Generator Architecture for GANs (StyleGAN), presents a novel model which addresses this challenge, while yielding state-of-the-art results in the generation of images.

In this work we experiment and exploit these features, within the latent space that StyleGAN provides us, to control the generation of faces, ultimately creating an interface for the use of StyleGAN's generative model and its style mixing properties to maintain and change specific features of the generated faces. Thus, the laboratory will be able to conduct experiments involving fake memories and face shapes, using their own customized artificial faces.