StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation

TL;DR

StarGAN introduces a scalable, single-model approach for multi-domain image-to-image translation, enabling flexible and high-quality translations across multiple domains with improved robustness and efficiency.

Contribution

It presents StarGAN, a novel unified model architecture that handles multiple domains simultaneously, overcoming scalability issues of previous pairwise models.

Findings

Outperforms existing models in translation quality

Successfully handles multiple domains with a single model

Demonstrates effectiveness on facial attribute transfer and expression synthesis

Abstract

Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. Such a unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network. This leads to StarGAN's superior quality of translated images compared to existing models as well as the novel capability of flexibly translating an input image to any desired target domain. We empirically demonstrate the effectiveness of our approach on a facial attribute transfer and a facial expression synthesis tasks.