{"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/multi-content-gan-for-few-shot-font-style","title":"Multi-Content GAN for Few-Shot Font Style Transfer","arxiv_id":"1712.00516","date":"2017-12-01","proceeding":"CVPR 2018 6","authors":["Samaneh Azadi","Matthew Fisher","Vladimir Kim","Zhaowen Wang","Eli Shechtman","Trevor Darrell"],"abstract":"In this work, we focus on the challenge of taking partial observations of\nhighly-stylized text and generalizing the observations to generate unobserved\nglyphs in the ornamented typeface. To generate a set of multi-content images\nfollowing a consistent style from very few examples, we propose an end-to-end\nstacked conditional GAN model considering content along channels and style\nalong network layers. Our proposed network transfers the style of given glyphs\nto the contents of unseen ones, capturing highly stylized fonts found in the\nreal-world such as those on movie posters or infographics. We seek to transfer\nboth the typographic stylization (ex. serifs and ears) as well as the textual\nstylization (ex. color gradients and effects.) We base our experiments on our\ncollected data set including 10,000 fonts with different styles and demonstrate\neffective generalization from a very small number of observed glyphs.","url_abs":"http://arxiv.org/abs/1712.00516v1","url_pdf":"http://arxiv.org/pdf/1712.00516v1.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":"multi-content-gan-for-few-shot-font-style","repo_url":"https://github.com/azadis/MC-GAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-content-gan-for-few-shot-font-style","repo_url":"https://github.com/JamesLiao714/MC_GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-content-gan-for-few-shot-font-style","repo_url":"https://github.com/Ryan0v0/Google_ML_Camp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-content-gan-for-few-shot-font-style","repo_url":"https://github.com/hologerry/AGIS-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-content-gan-for-few-shot-font-style","repo_url":"https://github.com/ptraverse/MC-GAN3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-content-gan-for-few-shot-font-style","repo_url":"https://github.com/zhourunlong/mc-gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"font-style-transfer","task_name":"Font Style Transfer"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.00516","atlas_url":"https://app.syntology.ai/?focus=1712.00516","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}