Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domains
arXiv:2010.05334
Abstract
GANs can generate photo-realistic images from the domain of their training data. However, those wanting to use them for creative purposes often want to generate imagery from a truly novel domain, a task which GANs are inherently unable to do. It is also desirable to have a level of control so that there is a degree of artistic direction rather than purely curation of random results. Here we present a method for interpolating between generative models of the StyleGAN architecture in a resolution dependent manner. This allows us to generate images from an entirely novel domain and do this with a degree of control over the nature of the output.
2 pages, 3 figures. Accepted to Machine Learning for Creativity and Design NeurIPS 2020 Workshop; Corrected typos
References in corpus (1)
Cited by in corpus (8)
- Face Generation and Editing with StyleGAN: A Survey
- CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis
- StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation
- Unsupervised Image-to-Image Translation via Pre-trained StyleGAN2 Network
- Active Divergence with Generative Deep Learning -- A Survey and Taxonomy
- Ukiyo-e Analysis and Creativity with Attribute and Geometry Annotation
- Fine-Tuning StyleGAN2 For Cartoon Face Generation
- StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN