{"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/typeface-completion-with-generative","title":"Typeface Completion with Generative Adversarial Networks","arxiv_id":"1811.03762","date":"2018-11-09","proceeding":null,"authors":["Yonggyu Park","Junhyun Lee","Yookyung Koh","Inyeop Lee","Jinhyuk Lee","Jaewoo Kang"],"abstract":"The mood of a text and the intention of the writer can be reflected in the\ntypeface. However, in designing a typeface, it is difficult to keep the style\nof various characters consistent, especially for languages with lots of\nmorphological variations such as Chinese. In this paper, we propose a Typeface\nCompletion Network (TCN) which takes one character as an input, and\nautomatically completes the entire set of characters in the same style as the\ninput characters. Unlike existing models proposed for image-to-image\ntranslation, TCN embeds a character image into two separate vectors\nrepresenting typeface and content. Combined with a reconstruction loss from the\nlatent space, and with other various losses, TCN overcomes the inherent\ndifficulty in designing a typeface. Also, compared to previous image-to-image\ntranslation models, TCN generates high quality character images of the same\ntypeface with a much smaller number of model parameters. We validate our\nproposed model on the Chinese and English character datasets, which is paired\ndata, and the CelebA dataset, which is unpaired data. In these datasets, TCN\noutperforms recently proposed state-of-the-art models for image-to-image\ntranslation. The source code of our model is available at\nhttps://github.com/yongqyu/TCN.","url_abs":"http://arxiv.org/abs/1811.03762v2","url_pdf":"http://arxiv.org/pdf/1811.03762v2.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":"typeface-completion-with-generative","repo_url":"https://github.com/yongqyu/TCN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"typeface-completion-with-generative","repo_url":"https://github.com/Pengxiao-Wang/Typeface-and-Font-Style-Transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"font-style-transfer","task_name":"Font Style Transfer"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"typeface-completion","task_name":"Typeface Completion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}