Creative Portraiture: Exploring Creative Adversarial Networks and Conditional Creative Adversarial Networks
This work addresses the problem of generating creative and novel images in AI art for researchers and artists, though it appears incremental as an extension of existing GAN methods.
The paper tackled the limitation of DCGANs in generating creative products by exploring creative adversarial networks (CANs) and introducing conditional creative adversarial networks (CCANs), resulting in the generation of novel portraits from the WikiArt dataset and style-conditioned creative portraits.
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.