Can I read Revisiting Latent Space of GAN Inversion for Real Image Editing on EtoBox?

Revisiting Latent Space of GAN Inversion for Real Image Editing by Katsumata, Kai; Vo, Duc Minh; Liu, Bei; Nakayama, Hideki is a scholarly article available to read on EtoBox.

What is Revisiting Latent Space of GAN Inversion for Real Image Editing about?

The exploration of the latent space in StyleGANs and GAN inversion exemplify impressive real-world image editing, yet the trade-off between reconstruction quality and editing quality remains an open problem. In this study, we revisit StyleGANs' hyperspherical prior $\mathcal{Z}$ and combine it with highly capable latent spaces to build combined spaces that faithfully invert real images while maintaining the quality of edited images. More specifically, we propose $\mathcal{F}/\mathcal{Z}^{+}$ space consisting of two subspaces: $\mathcal{F}$ space of an intermediate feature map of StyleGANs enabling faithful reconstruction and $\mathcal{Z}^{+}$ space of an extended StyleGAN prior supporting high editing quality. We project the real images into the proposed space to obtain the inverted codes, by which we then move along $\mathcal{Z}^{+}$, enabling semantic editing without sacrificing image quality. Comprehensive experiments show that $\mathcal{Z}^{+}$ can replace the most commonly-used $\mathcal{W}$, $\mathcal{W}^{+}$, and $\mathcal{S}$ spaces while preserving reconstruction quality, resulting in reduced distortion of edited images.

Author

Katsumata, Kai; Vo, Duc Minh; Liu, Bei; Nakayama, Hideki

Published

2023

Language

EN