Revisiting Latent Space of GAN Inversion for Robust Real Image Editing

Kai Katsumata, Duc Minh Vo, Bei Liu, Hideki Nakayama; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, pp. 5313-5322

We present a generative adversarial network (GAN) inversion with high reconstruction and editing quality. GAN inversion algorithms with expressive latent spaces produce near-perfect inversion but are not robust to editing operations in latent space, leading to undesirable edited images, a phenomenon known as the trade-off between reconstruction and editing quality. To cope with the trade-off, we revisit the hyperspherical prior of StyleGANs Z and propose to combine an extended space of Z with highly capable inversion algorithms. Our approach maintains the reconstruction quality of seminal GAN inversion methods while improving their editing quality owing to the constrained nature of Z. Through comprehensive experiments with several GAN inversion algorithms, we demonstrate that our approach enhances image editing quality in 2D/3D GANs.