Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domains
This addresses the need for more artistic direction in image generation for creative applications, though it appears incremental as it builds on existing StyleGAN architecture.
The paper tackles the problem of GANs being unable to generate images from novel domains and lacking control for creative use, by introducing a resolution-dependent interpolation method for StyleGAN models that enables controllable synthesis between domains.
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.