SwipeGANSpace: Swipe-to-Compare Image Generation via Efficient Latent Space Exploration

arXiv:2404.19693v1 Announce Type: cross
Abstract: 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 …

abstract adversarial arxiv cs.cv cs.hc exploration explore gans generate generative generative adversarial networks image image generation images interactions nature networks novel simple space study type via