GANs and Artificial Facial Expressions in Synthetic Portraits

Pilar Rosado,Rubén Fernández,Ferran Reverter

doi:10.3390/bdcc5040063

Abstract

Generative adversarial networks (GANs) provide powerful architectures for deep generative learning. GANs have enabled us to achieve an unprecedented degree of realism in the creation of synthetic images of human faces, landscapes, and buildings, among others. Not only image generation, but also image manipulation is possible with GANs. Generative deep learning models are inherently limited in their creative abilities because of a focus on learning for perfection. We investigated the potential of GAN’s latent spaces to encode human expressions, highlighting creative interest for suboptimal solutions rather than perfect reproductions, in pursuit of the artistic concept. We have trained Deep Convolutional GAN (DCGAN) and StyleGAN using a collection of portraits of detained persons, portraits of dead people who died of violent causes, and people whose portraits were taken during an orgasm. We present results which diverge from standard usage of GANs with the specific intention of producing portraits that may assist us in the representation and recognition of otherness in contemporary identity construction.

Highlights

Genetics, Microbiology and Statistics, University of Barcelona, 08028 Barcelona, Spain; Abstract: Generative adversarial networks (GANs) provide powerful architectures for deep generative learning
The project began with the creation and publication of a book under the same title [22] that consisted of a 21 foot-long (7 meters) leporello
The dataset the GAN is trained on is the key to its creativity

Summary

Introduction

Microbiology and Statistics, University of Barcelona, 08028 Barcelona, Spain; Abstract: Generative adversarial networks (GANs) provide powerful architectures for deep generative learning. In 2014, researcher Ian Goodfellow and his colleagues invented a new generative model of deep learning known as generative adversarial network (GAN) [1]. GANs apply in image processing and computer vision, natural language processing, music, speech and audio, medical field, data science, etc. They have been widely studied since 2014 and different variants have evolved. Introduce the so called Pix2Pix model in which implement a conditional GAN to image-toimage translation problems. They are conditional because instead of starting the generator

Results

Discussion

Conclusion