Image2StyleGAN++: How to Edit the Embedded Images?

Rameen Abdal, Yipeng Qin, Peter Wonka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

318 Scopus citations


We propose Image2StyleGAN++, a flexible image editing framework with many applications. Our framework extends the recent Image2StyleGAN in three ways. First, we introduce noise optimization as a complement to the W+ latent space embedding. Our noise optimization can restore high frequency features in images and thus significantly improves the quality of reconstructed images, e.g. a big increase of PSNR from 20 dB to 45 dB. Second, we extend the global W+ latent space embedding to enable local embeddings. Third, we combine embedding with activation tensor manipulation to perform high quality local edits along with global semantic edits on images. Such edits motivate various high quality image editing applications, e.g. image reconstruction, image inpainting, image crossover, local style transfer, image editing using scribbles, and attribute level feature transfer. Examples of the edited images are shown across the paper for visual inspection.
Original languageEnglish (US)
Title of host publication2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
ISBN (Print)978-1-7281-7169-2
StatePublished - 2020

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledged KAUST grant number(s): CRG2018-3730
Acknowledgements: This work was supported by the KAUST Office of Sponsored Research (OSR) under Award No. OSR-CRG2018-3730.


Dive into the research topics of 'Image2StyleGAN++: How to Edit the Embedded Images?'. Together they form a unique fingerprint.

Cite this