Unsupervised Image-to-Image Translation Networks | Research


12 bookmarks. First posted by lorz 13 days ago.


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.
6 days ago by jbenton
Copyright (C) 2017 NVIDIA Corporation. All rights reserved. Licensed under the CC BY-NC-ND 4.0 license
Archive 
11 days ago by plouf
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.
ai  hoax  ml  images 
11 days ago by paulbradshaw
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. 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. Copyright (C) 2017 NVIDIA Corporation.
11 days ago by sechilds
Favorite tweet:

The biggest casualty to AI won't be jobs, but the final and complete eradication of trust in anything you see or hear. https://t.co/sg9o4v2Q3f http://pic.twitter.com/nkj007LtEF

— Oli Franklin-Wallis (@olifranklin) December 4, 2017
IFTTT  Twitter 
12 days ago by mlcdf
Copyright (C) 2017 NVIDIA Corporation. All rights reserved. Licensed under the CC BY-NC-ND 4.0 license
12 days ago by simonings
How future instagram models will make their butts look bigger and get away with it
from twitter_favs
13 days ago by gyaresu
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.
ai  machinelearning  computervision 
13 days ago by florian.eckerstorfer