Creative Portraiture: Exploring Creative Adversarial Networks and Conditional Creative Adversarial Networks

TL;DR

This paper introduces creative adversarial networks (CANs) and conditional CANs (CCANs) to generate novel, style-conditioned creative portraits, addressing limitations of traditional GANs in producing truly creative outputs.

Contribution

The paper presents the development of CANs and CCANs, extending GANs to generate more creative and style-conditioned portraits, closely mimicking human creative processes.

Findings

CANs generate novel creative portraits from the WikiArt dataset.

CCANs produce style-conditioned portraits, demonstrating controlled creativity.

The methods emulate human-like creative processes by conditioning on style labels.

Abstract

Convolutional neural networks (CNNs) have been combined with generative adversarial networks (GANs) to create deep convolutional generative adversarial networks (DCGANs) with great success. DCGANs have been used for generating images and videos from creative domains such as fashion design and painting. A common critique of the use of DCGANs in creative applications is that they are limited in their ability to generate creative products because the generator simply learns to copy the training distribution. We explore an extension of DCGANs, creative adversarial networks (CANs). Using CANs, we generate novel, creative portraits, using the WikiArt dataset to train the network. Moreover, we introduce our extension of CANs, conditional creative adversarial networks (CCANs), and demonstrate their potential to generate creative portraits conditioned on a style label. We argue that generating products that are conditioned, or inspired, on a style label closely emulates real creative processes in which humans produce imaginative work that is still rooted in previous styles.