Evolution of Images with Diversity and Constraints Using a Generator Network
arXiv:1802.05480
Abstract
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.
References in corpus (4)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Texture Synthesis Using Convolutional Neural Networks
- Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
- The Evolutionary Process of Image Transition in Conjunction with Box and Strip Mutation