Toward Multimodal Image-to-Image Translation

NeurIPS 2017 Jun-Yan ZhuRichard ZhangDeepak PathakTrevor DarrellAlexei A. EfrosOliver WangEli Shechtman

Many image-to-image translation problems are ambiguous, as a single input image may correspond to multiple possible outputs. In this work, we aim to model a \emph{distribution} of possible outputs in a conditional generative modeling setting... (read more)

PDF Abstract
Task Dataset Model Metric name Metric value Global rank Compare
Multimodal Unsupervised Image-To-Image Translation Edge-to-Handbags BicycleGAN Quality 51.2% # 1
Multimodal Unsupervised Image-To-Image Translation Edge-to-Handbags BicycleGAN Diversity 0.140 # 2
Multimodal Unsupervised Image-To-Image Translation Edge-to-Shoes BicycleGAN Quality 56.7% # 1
Multimodal Unsupervised Image-To-Image Translation Edge-to-Shoes BicycleGAN Diversity 0.104 # 2