{"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/style-transfer-via-texture-synthesis","title":"Style-Transfer via Texture-Synthesis","arxiv_id":"1609.03057","date":"2016-09-10","proceeding":null,"authors":["Michael Elad","Peyman Milanfar"],"abstract":"Style-transfer is a process of migrating a style from a given image to the\ncontent of another, synthesizing a new image which is an artistic mixture of\nthe two. Recent work on this problem adopting Convolutional Neural-networks\n(CNN) ignited a renewed interest in this field, due to the very impressive\nresults obtained. There exists an alternative path towards handling the\nstyle-transfer task, via generalization of texture-synthesis algorithms. This\napproach has been proposed over the years, but its results are typically less\nimpressive compared to the CNN ones.\n  In this work we propose a novel style-transfer algorithm that extends the\ntexture-synthesis work of Kwatra et. al. (2005), while aiming to get stylized\nimages that get closer in quality to the CNN ones. We modify Kwatra's algorithm\nin several key ways in order to achieve the desired transfer, with emphasis on\na consistent way for keeping the content intact in selected regions, while\nproducing hallucinated and rich style in others. The results obtained are\nvisually pleasing and diverse, shown to be competitive with the recent CNN\nstyle-transfer algorithms. The proposed algorithm is fast and flexible, being\nable to process any pair of content + style images.","url_abs":"http://arxiv.org/abs/1609.03057v3","url_pdf":"http://arxiv.org/pdf/1609.03057v3.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":"style-transfer-via-texture-synthesis","repo_url":"https://github.com/DarkGeekMS/artistic-style-transfer-using-texture-synthesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"style-transfer-via-texture-synthesis","repo_url":"https://github.com/jsonkung/style-transfer-texture-synthesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"texture-synthesis","task_name":"Texture Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1609.03057","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}