{"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/stroke-controllable-fast-style-transfer-with","title":"Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields","arxiv_id":"1802.07101","date":"2018-02-20","proceeding":"ECCV 2018 9","authors":["Yongcheng Jing","Yang Liu","Yezhou Yang","Zunlei Feng","Yizhou Yu","DaCheng Tao","Mingli Song"],"abstract":"The Fast Style Transfer methods have been recently proposed to transfer a\nphotograph to an artistic style in real-time. This task involves controlling\nthe stroke size in the stylized results, which remains an open challenge. In\nthis paper, we present a stroke controllable style transfer network that can\nachieve continuous and spatial stroke size control. By analyzing the factors\nthat influence the stroke size, we propose to explicitly account for the\nreceptive field and the style image scales. We propose a StrokePyramid module\nto endow the network with adaptive receptive fields, and two training\nstrategies to achieve faster convergence and augment new stroke sizes upon a\ntrained model respectively. By combining the proposed runtime control\nstrategies, our network can achieve continuous changes in stroke sizes and\nproduce distinct stroke sizes in different spatial regions within the same\noutput image.","url_abs":"http://arxiv.org/abs/1802.07101v4","url_pdf":"http://arxiv.org/pdf/1802.07101v4.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":"stroke-controllable-fast-style-transfer-with","repo_url":"https://github.com/LouieYang/stroke-controllable-fast-style-transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.07101","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}