For successful semantic editing of real images, it is critical for a GAN inversion method to find an in-domain latent code that aligns with the domain of a pre-trained GAN model. Unfortunately, such in-domain latent codes can be found only for in-range images that align with the training images of a GAN model. In this paper, we propose BDInvert, a novel GAN inversion approach to semantic editing of out-of-range images that are geometrically unaligned with the training images of a GAN model. To find a latent code that is semantically editable, BDInvert inverts an input out-of-range image into an alternative latent space than the original latent space. We also propose a regularized inversion method to find a solution that supports semantic editing in the alternative space. Our experiments show that BDInvert effectively supports semantic editing of out-of-range images with geometric transformations.
@article{arxiv.2108.08998,
title = {GAN Inversion for Out-of-Range Images with Geometric Transformations},
author = {Kyoungkook Kang and Seongtae Kim and Sunghyun Cho},
journal= {arXiv preprint arXiv:2108.08998},
year = {2021}
}
Comments
Accepted to ICCV 2021. For supplementary material, see https://kkang831.github.io/publication/ICCV_2021_BDInvert/