Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Image2StyleGAN: How to embed images into the styleGAN latent space?

Abdal, Rameen, Qin, Yipeng ORCID: https://orcid.org/0000-0002-1551-9126 and Wonka, Peter 2019. Image2StyleGAN: How to embed images into the styleGAN latent space? Presented at: International Conference on Computer Vision (ICCV) 2019, Seoul, South Korea, 27 October 2019 - 3 November 2019. Proceedings of the International Conference on Computer Vision (ICCV) 2019. IEEE, pp. 4431-4440. \10.1109/ICCV.2019.00453

[thumbnail of ICCV_StyleGAN_HQ.pdf]
Preview
PDF - Accepted Post-Print Version
Download (79MB) | Preview

Abstract

We propose an efficient algorithm to embed a given image into the latent space of StyleGAN. This embedding enables semantic image editing operations that can be applied to existing photographs. Taking the StyleGAN trained on the FFHD dataset as an example, we show results for image morphing, style transfer, and expression transfer. Studying the results of the embedding algorithm provides valuable insights into the structure of the StyleGAN latent space. We propose a set of experiments to test what class of images can be embedded, how they are embedded, what latent space is suitable for embedding, and if the embedding is semantically meaningful.

Item Type: Conference or Workshop Item (Paper)
Date Type: Published Online
Status: Published
Schools: Computer Science & Informatics
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Publisher: IEEE
ISBN: 9781728148038
Date of First Compliant Deposit: 9 September 2019
Date of Acceptance: 22 July 2019
Last Modified: 26 Oct 2022 07:37
URI: https://orca.cardiff.ac.uk/id/eprint/125332

Citation Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics