Authors:
So Honda
;
Ryohei Orihara
;
Yuichi Sei
;
Yasuyuki Tahara
and
Akihiko Ohsuga
Affiliation:
The University of Electro-Communications, Tokyo, Japan
Keyword(s):
GAN Inversion, StyleGAN, StyleMap, Editability, Local Editing.
Abstract:
Recently, the field of GAN Inversion, which estimates the latent code of a GAN to reproduce the desired image, has attracted much attention. Once a latent variable that reproduces the input image is obtained, the image can be edited by manipulating the latent code. However, it is known that there is a trade-off between reconstruction quality, which is the difference between the input image and the reproduced image, and editability, which is the plausibility of the edited image. In our study, we attempted to improve reconstruction quality by extending latent code that represents the properties of the entire image in the spatial direction. Next, since such an expansion significantly impairs the editing quality, we performed a GAN Inversion that realizes both reconstruction quality and editability by imposing an additional regularization. As a result, the proposed method yielded a better trade-off between the reconstruction quality and the editability against the baseline from both quan
titative and qualitative perspectives, and is comparable to state-of-the-art(SOTA) methods that adjust the weights of the generators.
(More)