GANravel: User-Driven Direction Disentanglement in Generative Adversarial Networks

Generative adversarial networks (GANs) have many application over how to improve editing directions through disentanglement. areas including image editing, domain translation, missing data imputation, and support for creative work. However, GANs are considered 'black boxes'. Specifcally, the end-users have little control over how to improve editing directions through disentanglement. Prior work focused on new GAN architectures to disentangle editing directions. Alternatively, we propose GAN(RAVEL-a) user-driven direction disentanglement tool that complements the existing GAN architectures and allows users to improve editing directions iteratively. In two user studies with 16 participants each, GAN(RAVEL) users were able to disentangle directions and outperformed the state-of-the-art direction discovery baselines in disentanglement performance. In the second user study, GAN(RAVEL) was used in a creative task of creating dog memes and was able to create high-quality edited images and GIFs.