Balancing Reconstruction and Editing Quality of GAN Inversion for Real Image Editing with StyleGAN Prior Latent Space
This work addresses a key bottleneck in GAN-based image editing for researchers and practitioners, though it is incremental as it builds on existing GAN inversion methods.
The paper tackles the trade-off between reconstruction and editing quality in GAN inversion for real image editing with StyleGAN, by integrating hyperspherical prior spaces to improve editing quality without sacrificing image fidelity. Experiments show that the proposed Z+ space can replace common latent spaces, reducing distortion in edited images.
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 $\mathcal{Z}^+$ and integrate them into seminal GAN inversion methods to improve editing quality. Besides faithful reconstruction, our extensions achieve sophisticated editing quality with the aid of the StyleGAN prior. 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.