Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorZhang, Xijueen_US
dc.identifier.citationZhang, X. (2022). Towards superior control in automatic face editing with generative adversarial networks. Final Year Project (FYP), Nanyang Technological University, Singapore.
dc.description.abstractGenerative Adversarial Networks (GANs) have been widely used in image manipulation tasks such as local editing and image interpolation. This project examines StyleMapGAN, a novel approach that evolves from StyleGAN by replacing AdaIN with intermediate latent space carrying information on spatial dimensions, hence capable of performing high-quality local editing. In addition, by introducing a BiSeNet-based face parsing model, this project develops a fully automated process in local editing of human faces that only takes a few seconds. This project demonstrates that the face parsing model outputs masks that rivals manually labelled face datasets. Furthermore, this project explores more controls in local editing by introducing a pair of unaligned masks during stylemap mixing in W+ space in the generator. Local editing with interpolation is achieved and a demo application is developed to demonstrate the local editing process.en_US
dc.publisherNanyang Technological Universityen_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleTowards superior control in automatic face editing with generative adversarial networksen_US
dc.typeFinal Year Project (FYP)en_US
dc.contributor.supervisorChen Change Loyen_US
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.description.degreeBachelor of Engineering (Computer Science)en_US
item.fulltextWith Fulltext-
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)
Files in This Item:
File Description SizeFormat 
  Restricted Access
3.92 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 27, 2022


Updated on Jun 27, 2022

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.