Face transformation using StyleGAN

Face transformation using StyleGAN

This paper describes a simple method to discover controls for StyleGAN image synthesis. Important latent directions were derived from a linear Support Vector Machine classifier and regressor. Then, it was shown that these directions could be used to transform human faces; such as changing the gend...

Full description

Saved in:
Bibliographic Details
Main Author: Chua, Zhong En
Other Authors: Tan Yap Peng
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Online Access:https://hdl.handle.net/10356/157317
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:This paper describes a simple method to discover controls for StyleGAN image synthesis. Important latent directions were derived from a linear Support Vector Machine classifier and regressor. Then, it was shown that these directions could be used to transform human faces; such as changing the gender, hair length, head position, smile and more.

Similar Items