Image2StyleGAN++: How to Edit the Embedded Images?
This work provides incremental improvements for image editing applications, such as inpainting and style transfer, by enhancing existing methods.
The authors tackled the problem of flexible image editing by extending Image2StyleGAN to improve reconstruction quality and enable local edits, achieving a significant increase in PSNR from 20 dB to 45 dB.
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.