Unsupervised Image Translation Using Multi-Scale Residual GAN

Yifei Zhang (), Weipeng Li, Daling Wang and Shi Feng
Additional contact information
Yifei Zhang: School of Computer Science and Engineering, Northeastern University, Shenyang 110169, China
Weipeng Li: School of Computer Science and Engineering, Northeastern University, Shenyang 110169, China
Daling Wang: School of Computer Science and Engineering, Northeastern University, Shenyang 110169, China
Shi Feng: School of Computer Science and Engineering, Northeastern University, Shenyang 110169, China

Mathematics, 2022, vol. 10, issue 22, 1-16

Abstract: Image translation is a classic problem of image processing and computer vision for transforming an image from one domain to another by learning the mapping between an input image and an output image. A novel Multi-scale Residual Generative Adversarial Network (MRGAN) based on unsupervised learning is proposed in this paper for transforming images between different domains using unpaired data. In the model, a dual generater architecture is used to eliminate the dependence on paired training samples and introduce a multi-scale layered residual network in generators for reducing semantic loss of images in the process of encoding. The Wasserstein GAN architecture with gradient penalty (WGAN-GP) is employed in the discriminator to optimize the training process and speed up the network convergence. Comparative experiments on several image translation tasks over style transfers and object migrations show that the proposed MRGAN outperforms strong baseline models by large margins.

Keywords: image translation; generative adversarial network; unsupervised learning; object migration; multi-scale residual network (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/22/4347/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/22/4347/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:22:p:4347-:d:977684

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().