Evolution of Images with Diversity and Constraints Using a Generator Network
This work addresses the incremental challenge of applying evolutionary methods to latent spaces for aesthetic image generation, which could benefit artists and researchers in computational creativity.
The authors tackled the problem of generating artistic images by using evolutionary search in the latent space of a generative network, focusing on optimizing aesthetic feature scores for faces and butterflies datasets, and demonstrated interactions between these measures.
Evolutionary search has been extensively used to generate artistic images. Raw images have high dimensionality which makes a direct search for an image challenging. In previous work this problem has been addressed by using compact symbolic encodings or by constraining images with priors. Recent developments in deep learning have enabled a generation of compelling artistic images using generative networks that encode images with lower-dimensional latent spaces. To date this work has focused on the generation of images concordant with one or more classes and transfer of artistic styles. There is currently no work which uses search in this latent space to generate images scoring high or low aesthetic measures. In this paper we use evolutionary methods to search for images in two datasets, faces and butterflies, and demonstrate the effect of optimising aesthetic feature scores in one or two dimensions. The work gives a preliminary indication of which feature measures promote the most interesting images and how some of these measures interact.