Controlled Modification of Generated (Style)GAN Latent Vectors

Title

Controlled Modification of Generated (Style)GAN Latent Vectors

 Author

Liu, Yifei (TU Delft Electrical Engineering, Mathematics and Computer Science)

Contributor

Viering, Tom (graduation committee)
Tax, David (mentor)

Degree granting institution

Delft University of Technology

 Date

2019-06-28

 Abstract

StyleGAN is a neural network architecture that is able to generate photo-realistic images. The diversity of generated images are ensured by latent vectors. These latent vectors encodes important features of generated images. They provide us insight-full information about properties of image generation in StyleGAN, which may also occur similarly in other neural network architectures. Using pre-trained StyleGAN models, we have conducted several experiments to show properties on StyleGAN based on results of style modification. The experiments have shown the influence of noise and styles in StyleGAN and how latent vectors can be manipulated in generated images.

 To reference this document use:

http://resolver.tudelft.nl/uuid:01fcea28-7477-45d8-baa2-71b29bb07fc2

 Part of collection

Student theses

 Document type

bachelor thesis

 Rights

© 2019 Yifei Liu
Files
PDF BEP_paper_1_.pdf 12.58 MB
Close viewer