[1O4-GS-7] Vision, speech media processing

[1O4-GS-7-04] What GAN Inversion works best with NaviGAN in face image editing? An Experimental Study.

〇Shun Kitagawa¹, Taro Hatakeyama¹, Komei Hiruta¹, Atsushi Hashimoto^2,1, Satoshi Kurihara¹ (1. Keio University, 2. OMRON SINIC X Corporation)

Keywords:GAN, Image Editing, GAN Inversion, Face Image, Deep Generative Model

In this paper, we edit real images to out-of-distribution (OOD) images by combining NaviGAN and GAN Inversion. NaviGAN is a GAN technique to modify generated results, generally in-distribution of training data, to OOD ones. When NaviGAN is applied to real images, GAN Inversion is required to embed real images into the GAN latent space. We aim to use this combination to exaggerate specific parts of real face images while maintaining their identity. Among various GAN Inversion methods, we found methods included in fine-tuning type are the best to be combined with NaviGAN. Thus, we propose the combination of the fine-tuning type method and NaviGAN for our goal. Compared to other methods, in experiments, we confirmed that the proposed combination achieves the best exaggeration of specific parts while maintaining identities. Additionally, we show that our method can be applied not only to real pictures but to Manga characters.