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

CVPR 2018 Yunjey ChoiMinje ChoiMunyoung KimJung-Woo HaSunghun KimJaegul Choo

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... (read more)

PDF Abstract

Results from the Paper


 SOTA for Image-to-Image Translation on RaFD (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT LEADERBOARD
Image-to-Image Translation RaFD StarGAN Classification Error 2.12% # 1

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
SOURCE PAPER COMPARE
Facial Expression Translation CelebA StarGAN AMT 14.8 # 4