Make It So: Steering StyleGAN for Any Image Inversion and Editing

TL;DR

Make It So introduces a novel GAN inversion method operating in the noise space, significantly improving inversion accuracy and editing quality for real-world images, especially out-of-domain ones.

Contribution

The paper presents a new GAN inversion approach that works in the noise space, enhancing out-of-domain image editing and surpassing prior methods in accuracy and quality.

Findings

Outperforms PTI by a factor of five in inversion accuracy.

Achieves ten times better edit quality for complex indoor scenes.

Preserves editing capabilities for out-of-domain images.

Abstract

StyleGAN's disentangled style representation enables powerful image editing by manipulating the latent variables, but accurately mapping real-world images to their latent variables (GAN inversion) remains a challenge. Existing GAN inversion methods struggle to maintain editing directions and produce realistic results. To address these limitations, we propose Make It So, a novel GAN inversion method that operates in the $\mathcal{Z}$ (noise) space rather than the typical $\mathcal{W}$ (latent style) space. Make It So preserves editing capabilities, even for out-of-domain images. This is a crucial property that was overlooked in prior methods. Our quantitative evaluations demonstrate that Make It So outperforms the state-of-the-art method PTI~\cite{roich2021pivotal} by a factor of five in inversion accuracy and achieves ten times better edit quality for complex indoor scenes.