Cycle generative adversarial network for unpaired sketch-to-character translation

Cartoon characters are currently being used in various applications such as comic and cartoon production. The ability to generate a variety of poses and facial expression of cartoon characters from simple sketches of stickfigures can ease the drawing process in production. Previous studies show only...

Full description

Saved in:
Bibliographic Details
Main Author: Alsaati, Leena Zeini J.
Format: Thesis
Language:English
Published: 2019
Subjects:
Online Access:http://eprints.utm.my/id/eprint/96646/1/LeenaZeiniJAlsaatiMSC2019.pdf.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-utm-ep.96646
record_format uketd_dc
spelling my-utm-ep.966462022-08-15T04:42:07Z Cycle generative adversarial network for unpaired sketch-to-character translation 2019 Alsaati, Leena Zeini J. QA75 Electronic computers. Computer science Cartoon characters are currently being used in various applications such as comic and cartoon production. The ability to generate a variety of poses and facial expression of cartoon characters from simple sketches of stickfigures can ease the drawing process in production. Previous studies show only few research focused on the task of sketch to character translation. With low performance of detecting rare pose features and improving rare feature detection has not been significantly studied. The aim of our research is to investigate the capabilities of generative adversarial networks (GANs) in the application of Sketch to Character translation. A wide range of extended GAN versions has been reviewed and in this research, a new dataset collection has been proposed which consists of images of sketches and cartoon characters that are manually drawn. A Cycle GAN has been implemented and its performance against Conditional GAN is compared. Cycle GAN’s cycle consistent loss is the main reason for learning a mapping between the domain of source images and the domain of target images without the need of paired training samples. Cycle GAN has been proven successful in handling a verity of applications in unpaired translation setting. The Conditional GAN has been also proven successful in a wide range of applications, however, it requires paired training samples. Results show that Conditional outperforms the Cycle GAN in accurately mapping the cartoon characters to the stickfigure, which is due to the nature of the paired training sample. However, the Cycle GAN still managed to produce sharper images that compete with the results of a Conditional GAN. 2019 Thesis http://eprints.utm.my/id/eprint/96646/ http://eprints.utm.my/id/eprint/96646/1/LeenaZeiniJAlsaatiMSC2019.pdf.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:143196 masters Universiti Teknologi Malaysia Faculty of Engineering - School of Computing
institution Universiti Teknologi Malaysia
collection UTM Institutional Repository
language English
topic QA75 Electronic computers
Computer science
spellingShingle QA75 Electronic computers
Computer science
Alsaati, Leena Zeini J.
Cycle generative adversarial network for unpaired sketch-to-character translation
description Cartoon characters are currently being used in various applications such as comic and cartoon production. The ability to generate a variety of poses and facial expression of cartoon characters from simple sketches of stickfigures can ease the drawing process in production. Previous studies show only few research focused on the task of sketch to character translation. With low performance of detecting rare pose features and improving rare feature detection has not been significantly studied. The aim of our research is to investigate the capabilities of generative adversarial networks (GANs) in the application of Sketch to Character translation. A wide range of extended GAN versions has been reviewed and in this research, a new dataset collection has been proposed which consists of images of sketches and cartoon characters that are manually drawn. A Cycle GAN has been implemented and its performance against Conditional GAN is compared. Cycle GAN’s cycle consistent loss is the main reason for learning a mapping between the domain of source images and the domain of target images without the need of paired training samples. Cycle GAN has been proven successful in handling a verity of applications in unpaired translation setting. The Conditional GAN has been also proven successful in a wide range of applications, however, it requires paired training samples. Results show that Conditional outperforms the Cycle GAN in accurately mapping the cartoon characters to the stickfigure, which is due to the nature of the paired training sample. However, the Cycle GAN still managed to produce sharper images that compete with the results of a Conditional GAN.
format Thesis
qualification_level Master's degree
author Alsaati, Leena Zeini J.
author_facet Alsaati, Leena Zeini J.
author_sort Alsaati, Leena Zeini J.
title Cycle generative adversarial network for unpaired sketch-to-character translation
title_short Cycle generative adversarial network for unpaired sketch-to-character translation
title_full Cycle generative adversarial network for unpaired sketch-to-character translation
title_fullStr Cycle generative adversarial network for unpaired sketch-to-character translation
title_full_unstemmed Cycle generative adversarial network for unpaired sketch-to-character translation
title_sort cycle generative adversarial network for unpaired sketch-to-character translation
granting_institution Universiti Teknologi Malaysia
granting_department Faculty of Engineering - School of Computing
publishDate 2019
url http://eprints.utm.my/id/eprint/96646/1/LeenaZeiniJAlsaatiMSC2019.pdf.pdf
_version_ 1747818672698687488