GANs with Multiple Constraints for Image Translation

Unpaired image translation is a challenging problem in computer vision, while existing generative adversarial networks (GANs) models mainly use the adversarial loss and other constraints to model. But the degree of constraint imposed on the generator and the discriminator is not enough, which result...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan Gan, Junxin Gong, Mao Ye, Yang Qian, Kedi Liu, Su Zhang
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2018/4613935
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849413349615337472
author Yan Gan
Junxin Gong
Mao Ye
Yang Qian
Kedi Liu
Su Zhang
author_facet Yan Gan
Junxin Gong
Mao Ye
Yang Qian
Kedi Liu
Su Zhang
author_sort Yan Gan
collection DOAJ
description Unpaired image translation is a challenging problem in computer vision, while existing generative adversarial networks (GANs) models mainly use the adversarial loss and other constraints to model. But the degree of constraint imposed on the generator and the discriminator is not enough, which results in bad image quality. In addition, we find that the current GANs-based models have not yet been implemented by adding an auxiliary domain, which is used to constrain the generator. To solve the problem mentioned above, we propose a multiscale and multilevel GANs (MMGANs) model for image translation. In this model, we add an auxiliary domain to constrain generator, which combines this auxiliary domain with the original domains for modelling and helps generator learn the detailed content of the image. Then we use multiscale and multilevel feature matching to constrain the discriminator. The purpose is to make the training process as stable as possible. Finally, we conduct experiments on six image translation tasks. The results verify the validity of the proposed model.
format Article
id doaj-art-678e034d1acb4ac3ad938283626876ab
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-678e034d1acb4ac3ad938283626876ab2025-08-20T03:34:09ZengWileyComplexity1076-27871099-05262018-01-01201810.1155/2018/46139354613935GANs with Multiple Constraints for Image TranslationYan Gan0Junxin Gong1Mao Ye2Yang Qian3Kedi Liu4Su Zhang5School of Computer Science and Engineering, Key Laboratory for NeuroInformation of Ministry of Education, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, Key Laboratory for NeuroInformation of Ministry of Education, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, Key Laboratory for NeuroInformation of Ministry of Education, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, Key Laboratory for NeuroInformation of Ministry of Education, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, Key Laboratory for NeuroInformation of Ministry of Education, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaUnpaired image translation is a challenging problem in computer vision, while existing generative adversarial networks (GANs) models mainly use the adversarial loss and other constraints to model. But the degree of constraint imposed on the generator and the discriminator is not enough, which results in bad image quality. In addition, we find that the current GANs-based models have not yet been implemented by adding an auxiliary domain, which is used to constrain the generator. To solve the problem mentioned above, we propose a multiscale and multilevel GANs (MMGANs) model for image translation. In this model, we add an auxiliary domain to constrain generator, which combines this auxiliary domain with the original domains for modelling and helps generator learn the detailed content of the image. Then we use multiscale and multilevel feature matching to constrain the discriminator. The purpose is to make the training process as stable as possible. Finally, we conduct experiments on six image translation tasks. The results verify the validity of the proposed model.http://dx.doi.org/10.1155/2018/4613935
spellingShingle Yan Gan
Junxin Gong
Mao Ye
Yang Qian
Kedi Liu
Su Zhang
GANs with Multiple Constraints for Image Translation
Complexity
title GANs with Multiple Constraints for Image Translation
title_full GANs with Multiple Constraints for Image Translation
title_fullStr GANs with Multiple Constraints for Image Translation
title_full_unstemmed GANs with Multiple Constraints for Image Translation
title_short GANs with Multiple Constraints for Image Translation
title_sort gans with multiple constraints for image translation
url http://dx.doi.org/10.1155/2018/4613935
work_keys_str_mv AT yangan ganswithmultipleconstraintsforimagetranslation
AT junxingong ganswithmultipleconstraintsforimagetranslation
AT maoye ganswithmultipleconstraintsforimagetranslation
AT yangqian ganswithmultipleconstraintsforimagetranslation
AT kediliu ganswithmultipleconstraintsforimagetranslation
AT suzhang ganswithmultipleconstraintsforimagetranslation