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...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
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 |