Towards superior control in automatic face editing with generative adversarial networks

Generative 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 dim...

Full description

Saved in:
Bibliographic Details
Main Author: Zhang, Xijue
Other Authors: Chen Change Loy
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/156775
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-156775
record_format dspace
spelling sg-ntu-dr.10356-1567752022-04-23T12:32:39Z Towards superior control in automatic face editing with generative adversarial networks Zhang, Xijue Chen Change Loy School of Computer Science and Engineering ccloy@ntu.edu.sg Engineering::Computer science and engineering Generative 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. Bachelor of Engineering (Computer Science) 2022-04-23T12:32:39Z 2022-04-23T12:32:39Z 2022 Final Year Project (FYP) Zhang, X. (2022). Towards superior control in automatic face editing with generative adversarial networks. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156775 https://hdl.handle.net/10356/156775 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
spellingShingle Engineering::Computer science and engineering
Zhang, Xijue
Towards superior control in automatic face editing with generative adversarial networks
description Generative 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.
author2 Chen Change Loy
author_facet Chen Change Loy
Zhang, Xijue
format Final Year Project
author Zhang, Xijue
author_sort Zhang, Xijue
title Towards superior control in automatic face editing with generative adversarial networks
title_short Towards superior control in automatic face editing with generative adversarial networks
title_full Towards superior control in automatic face editing with generative adversarial networks
title_fullStr Towards superior control in automatic face editing with generative adversarial networks
title_full_unstemmed Towards superior control in automatic face editing with generative adversarial networks
title_sort towards superior control in automatic face editing with generative adversarial networks
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/156775
_version_ 1731235810158575616