[1O1-GS-7] Vision, speech media processing: GAN

[1O1-GS-7-01] Photo-to-Manga Faces Translation Based Conditional Generative Adversarial Networks

〇Taro Hatakeyama¹, Ryusuke Saito¹, Komei Hiruta¹, Atsushi Hashimoto^1,2, Satoshi Kurihara¹ (1. Keio University, 2. OMRON SINIC X Corp.)

Keywords:Conditional GAN, GAN Inversion, Deep Generative Model, Face, Manga

Manga is one of the representative cultures of Japan. In general, manga artists depict characters with black lines on a white background and describe their appearance and movements abstractly, while exaggerating their characteristics geometrically. Aiming to reproduce such information processing capabilities of humans computationally, we propose Conditional GAN Inversion, which is the application of GAN Inversion to Conditional GAN, to realize the translation from photos to manga faces. Conditional GAN learns multiple domains in a shared network. It enables geometrically large deformations and the preservation of the identity of original images. Experimental results show that our method generates high-quality manga faces preserving the drawing style and the identities compared to other related state-of-the-art methods.