SwipeGANSpace: Swipe-to-Compare Image Generation via Efficient Latent Space Exploration
This work addresses the problem of user-friendly image generation for creative applications, though it is incremental as it builds on existing GAN and interaction techniques.
The paper tackles the challenge of generating preferred images with GANs by introducing a swipe-based interaction method that uses PCA on StyleGAN's latent space and a multi-armed bandit algorithm to explore dimensions based on user preferences, resulting in more efficient image generation than baselines.
Generating preferred images using generative adversarial networks (GANs) is challenging owing to the high-dimensional nature of latent space. In this study, we propose a novel approach that uses simple user-swipe interactions to generate preferred images for users. To effectively explore the latent space with only swipe interactions, we apply principal component analysis to the latent space of the StyleGAN, creating meaningful subspaces. We use a multi-armed bandit algorithm to decide the dimensions to explore, focusing on the preferences of the user. Experiments show that our method is more efficient in generating preferred images than the baseline methods. Furthermore, changes in preferred images during image generation or the display of entirely different image styles were observed to provide new inspirations, subsequently altering user preferences. This highlights the dynamic nature of user preferences, which our proposed approach recognizes and enhances.