GANravel: User-Driven Direction Disentanglement in Generative Adversarial Networks
This addresses the 'black box' issue in GANs for end-users in applications like image editing and creative work, offering a complementary tool to existing architectures.
The paper tackles the problem of limited user control over editing directions in GANs, proposing GANravel, a user-driven tool that allows iterative improvement of directions, and in user studies, it outperformed state-of-the-art baselines in disentanglement performance and created high-quality edited images and GIFs.
Generative adversarial networks (GANs) have many application areas including image editing, domain translation, missing data imputation, and support for creative work. However, GANs are considered 'black boxes'. Specifically, 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 GANravel 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, GANravel users were able to disentangle directions and outperformed the state-of-the-art direction discovery baselines in disentanglement performance. In the second user study, GANravel was used in a creative task of creating dog memes and was able to create high-quality edited images and GIFs.