StarGAN v2: Diverse Image Synthesis for Multiple Domains

4 Dec 2019Yunjey ChoiYoungjung UhJaejun YooJung-Woo Ha

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... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Image-to-Image Translation AFHQ StarGAN v2 FID 24.4 # 1
LPIPS 0.524 # 1
Image-to-Image Translation CelebA-HQ StarGAN v2 FID 18.0 # 2
LPIPS 0.428 # 1