SOTAVerified

StarGAN v2: Diverse Image Synthesis for Multiple Domains

2019-12-04CVPR 2020Code Available1· sign in to hype

Yunjey Choi, Youngjung Uh, Jaejun Yoo, Jung-Woo Ha

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
AFHQStarGAN v2LPIPS0.52Unverified
CelebA-HQStarGAN v2FID13.73Unverified

Reproductions