Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

03/30/2017
by   Jun-Yan Zhu, et al.
0

Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training data will not be available. We present an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples. Our goal is to learn a mapping G: X → Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss. Because this mapping is highly under-constrained, we couple it with an inverse mapping F: Y → X and introduce a cycle consistency loss to push F(G(X)) ≈ X (and vice versa). Qualitative results are presented on several tasks where paired training data does not exist, including collection style transfer, object transfiguration, season transfer, photo enhancement, etc. Quantitative comparisons against several prior methods demonstrate the superiority of our approach.

READ FULL TEXT

page 6

page 8

page 10

page 11

page 12

page 13

page 14

page 15

research
03/05/2020

Generating Embroidery Patterns Using Image-to-Image Translation

In many scenarios in computer vision, machine learning, and computer gra...
research
07/08/2019

Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases

Dataset bias is a well-known problem in the field of computer vision. Th...
research
10/31/2020

Pose Randomization for Weakly Paired Image Style Translation

Utilizing the trained model under different conditions without data anno...
research
04/15/2019

Implicit Pairs for Boosting Unpaired Image-to-Image Translation

In image-to-image translation the goal is to learn a mapping from one im...
research
08/12/2022

CycleGAN with three different unpaired datasets

The original publication Unpaired Image-to-Image Translation using Cycle...
research
06/23/2020

Image-to-image Mapping with Many Domains by Sparse Attribute Transfer

Unsupervised image-to-image translation consists of learning a pair of m...
research
09/16/2018

Geometry-Consistent Adversarial Networks for One-Sided Unsupervised Domain Mapping

Unsupervised domain mapping aims at learning a function to translate dom...

Please sign up or login with your details

Forgot password? Click here to reset