2020/04/22 by Hao Su, Jianwei Niu, Su, Hao +9 · 2 citations
Computer Science · Psychology · #Advanced Vision and Imaging #Art #Artificial intelligence #Comics #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Exaggeration #FOS: Computer and information sciences #Face (sociological concept) #Generative Adversarial Networks and Image Synthesis #Image (mathematics) #Linguistics #Natural language processing #Psychology #Similarity (geometry) #Style (visual arts) #Translation (biology) #Video Analysis and Summarization #Visual arts #cs.CV
paper · pdf · doi:10.48550/arxiv.2004.10634
published in arXiv (Cornell University) (Cornell University) · 17 pages
openalex publication_date 2020/04/22 · arxiv created 2020/12/17 · arxiv updated 2020/12/18 · openalex created_date 2020/12/21 · openalex updated_date 2026/08/06
Manga is a world popular comic form originated in Japan, which typically employs black-and-white stroke lines and geometric exaggeration to describe humans' appearances, poses, and actions. In this paper, we propose MangaGAN, the first method based on Generative Adversarial Network (GAN) for unpaired photo-to-manga translation. Inspired by how experienced manga artists draw manga, MangaGAN generates the geometric features of manga face by a designed GAN model and delicately translates each facial region into the manga domain by a tailored multi-GANs architecture. For training MangaGAN, we construct a new dataset collected from a popular manga work, containing manga facial features, landmarks, bodies, and so on. Moreover, to produce high-quality manga faces, we further propose a structural smoothing loss to smooth stroke-lines and avoid noisy pixels, and a similarity preserving module to improve the similarity between domains of photo and manga. Extensive experiments show that MangaGAN can produce high-quality manga faces which preserve both the facial similarity and a popular manga style, and outperforms other related state-of-the-art methods.