{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/cgan-based-manga-colorization-using-a-single","title":"cGAN-based Manga Colorization Using a Single Training Image","arxiv_id":"1706.06918","date":"2017-06-21","proceeding":null,"authors":["Paulina Hensman","Kiyoharu Aizawa"],"abstract":"The Japanese comic format known as Manga is popular all over the world. It is\ntraditionally produced in black and white, and colorization is time consuming\nand costly. Automatic colorization methods generally rely on greyscale values,\nwhich are not present in manga. Furthermore, due to copyright protection,\ncolorized manga available for training is scarce. We propose a manga\ncolorization method based on conditional Generative Adversarial Networks\n(cGAN). Unlike previous cGAN approaches that use many hundreds or thousands of\ntraining images, our method requires only a single colorized reference image\nfor training, avoiding the need of a large dataset. Colorizing manga using\ncGANs can produce blurry results with artifacts, and the resolution is limited.\nWe therefore also propose a method of segmentation and color-correction to\nmitigate these issues. The final results are sharp, clear, and in high\nresolution, and stay true to the character's original color scheme.","url_abs":"http://arxiv.org/abs/1706.06918v1","url_pdf":"http://arxiv.org/pdf/1706.06918v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"cgan-based-manga-colorization-using-a-single","repo_url":"https://github.com/ryanliwag/cGan-Based-Manga-Colorization-using-1-training-image","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"colorization","task_name":"Colorization"}],"methods":[{"method_slug":"colorization","method_name":"Colorization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}