Unsupervised Image-to-Image Translation Networks

NeurIPS 2017  ·  Ming-Yu Liu, Thomas Breuel, Jan Kautz ·

Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions that can arrive the given marginal distributions, one could infer nothing about the joint distribution from the marginal distributions without additional assumptions. To address the problem, we make a shared-latent space assumption and propose an unsupervised image-to-image translation framework based on Coupled GANs. We compare the proposed framework with competing approaches and present high quality image translation results on various challenging unsupervised image translation tasks, including street scene image translation, animal image translation, and face image translation. We also apply the proposed framework to domain adaptation and achieve state-of-the-art performance on benchmark datasets. Code and additional results are available in https://github.com/mingyuliutw/unit .

PDF Abstract NeurIPS 2017 PDF NeurIPS 2017 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Multimodal Unsupervised Image-To-Image Translation Cats-and-Dogs UNIT CIS 0.115 # 2
IS 0.826 # 2
Multimodal Unsupervised Image-To-Image Translation Edge-to-Handbags UNIT Quality 37.3% # 4
Diversity 0.023 # 3
Multimodal Unsupervised Image-To-Image Translation Edge-to-Shoes UNIT Quality 37.4% # 3
Diversity 0.011 # 3
Multimodal Unsupervised Image-To-Image Translation EPFL NIR-VIS UNIT PSNR 15.33 # 3
Unsupervised Image-To-Image Translation Freiburg Forest Dataset UNIT PSNR 9.42 # 3

Methods


No methods listed for this paper. Add relevant methods here