StarGAN v2: Diverse Image Synthesis for Multiple Domains

TL;DR

StarGAN v2 is a unified image-to-image translation framework that achieves high diversity, quality, and scalability across multiple visual domains, outperforming previous methods.

Contribution

It introduces StarGAN v2, a novel single model capable of diverse, high-quality image translation across multiple domains, addressing limitations of prior approaches.

Findings

Outperforms baselines in visual quality and diversity

Handles multiple domains with a single model

Validated on CelebA-HQ and AFHQ datasets

Abstract

A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains. Existing methods address either of the issues, having limited diversity or multiple models for all domains. We propose StarGAN v2, a single framework that tackles both and shows significantly improved results over the baselines. Experiments on CelebA-HQ and a new animal faces dataset (AFHQ) validate our superiority in terms of visual quality, diversity, and scalability. To better assess image-to-image translation models, we release AFHQ, high-quality animal faces with large inter- and intra-domain differences. The code, pretrained models, and dataset can be found at https://github.com/clovaai/stargan-v2.