Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
Thesis.pdf (19.31 MB)
ETD Abstract Container
Abstract Header
Improving Image Realism by Traversing the GAN Latent Space
Author Info
Wen, Jeffrey
ORCID® Identifier
http://orcid.org/0000-0003-3001-4086
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=osu1638961569719525
Abstract Details
Year and Degree
2022, Master of Science, Ohio State University, Electrical and Computer Engineering.
Abstract
In just a few years, the photo-realism of images synthesized by Generative Adversarial Networks (GANs) has gone from somewhat reasonable to almost perfect largely by increasing the complexity of the networks, e.g., adding layers, intermediate latent spaces, style-transfer parameters, etc. This trajectory has led many of the state-of-the-art GANs to be inaccessibly large, disengaging many without large computational resources. Recognizing this, we explore a method for squeezing additional performance from existing, low-complexity GANs. Formally, we present an unsupervised method to find a direction in the latent space that aligns with improved photo-realism. Our approach leaves the network unchanged while enhancing the fidelity of the generated image. We use a simple generator inversion to find the direction in the latent space that results in the smallest change in the image space. Leveraging the learned structure of the latent space, we find moving in this direction corrects many image artifacts and presents a more realistic image. We verify our findings qualitatively and quantitatively, showing an improvement in Frechet Inception Distance (FID) exists along our trajectory which surpasses the original GAN and other approaches including a supervised method. We expand further and provide an optimization method to automatically select latent vectors along the path that balance the variation and realism of samples. We apply our method to several diverse datasets and three architectures of varying complexity to illustrate the generalizability of our approach. By expanding the utility of low-complexity and existing networks, we hope to encourage the democratization of GANs.
Committee
Abhishek Gupta (Committee Member)
Aleix Martinez (Advisor)
Pages
57 p.
Subject Headings
Electrical Engineering
Keywords
Generative Adversarial Networks
;
GAN
;
Latent Space
;
Image Generation
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Wen, J. (2022).
Improving Image Realism by Traversing the GAN Latent Space
[Master's thesis, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1638961569719525
APA Style (7th edition)
Wen, Jeffrey.
Improving Image Realism by Traversing the GAN Latent Space.
2022. Ohio State University, Master's thesis.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=osu1638961569719525.
MLA Style (8th edition)
Wen, Jeffrey. "Improving Image Realism by Traversing the GAN Latent Space." Master's thesis, Ohio State University, 2022. http://rave.ohiolink.edu/etdc/view?acc_num=osu1638961569719525
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
osu1638961569719525
Download Count:
202
Copyright Info
© 2022, some rights reserved.
Improving Image Realism by Traversing the GAN Latent Space by Jeffrey Wen is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License. Based on a work at etd.ohiolink.edu.
This open access ETD is published by The Ohio State University and OhioLINK.