Style Transfer on Face Portraits
André, Christophe
Promotor(s) : Geurts, Pierre
Date of defense : 9-Sep-2019/10-Sep-2019 • Permalink : http://hdl.handle.net/2268.2/8084
Details
Title : | Style Transfer on Face Portraits |
Translated title : | [fr] Transfert de style appliqué à des portraits |
Author : | André, Christophe |
Date of defense : | 9-Sep-2019/10-Sep-2019 |
Advisor(s) : | Geurts, Pierre |
Committee's member(s) : | Van Droogenbroeck, Marc
Gribomont, Pascal |
Language : | English |
Number of pages : | 57 |
Keywords : | [en] Computer Vision [en] Deep Learning [en] Style Transfer |
Discipline(s) : | Engineering, computing & technology > Computer science |
Target public : | Researchers Professionals of domain Student |
Complementary URL : | https://github.com/c-andre/master-thesis |
Institution(s) : | Université de Liège, Liège, Belgique |
Degree: | Master en ingénieur civil en informatique, à finalité spécialisée en "intelligent systems" |
Faculty: | Master thesis of the Faculté des Sciences appliquées |
Abstract
[en] The topic of style transfer, specialized for head portraits, is tackled in this thesis -- primarily through the lens of optimization-based neural style transfer algorithms. A new combination of some of these methods from the literature is proposed as a solution to the problem, after a thorough discussion of these techniques' pros and cons.
File(s)
Document(s)
Cite this master thesis
All documents available on MatheO are protected by copyright and subject to the usual rules for fair use.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.