{"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/stable-and-controllable-neural-texture","title":"Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses","arxiv_id":"1701.08893","date":"2017-01-31","proceeding":null,"authors":["Eric Risser","Pierre Wilmot","Connelly Barnes"],"abstract":"Recently, methods have been proposed that perform texture synthesis and style\ntransfer by using convolutional neural networks (e.g. Gatys et al.\n[2015,2016]). These methods are exciting because they can in some cases create\nresults with state-of-the-art quality. However, in this paper, we show these\nmethods also have limitations in texture quality, stability, requisite\nparameter tuning, and lack of user controls. This paper presents a multiscale\nsynthesis pipeline based on convolutional neural networks that ameliorates\nthese issues. We first give a mathematical explanation of the source of\ninstabilities in many previous approaches. We then improve these instabilities\nby using histogram losses to synthesize textures that better statistically\nmatch the exemplar. We also show how to integrate localized style losses in our\nmultiscale framework. These losses can improve the quality of large features,\nimprove the separation of content and style, and offer artistic controls such\nas paint by numbers. We demonstrate that our approach offers improved quality,\nconvergence in fewer iterations, and more stability over the optimization.","url_abs":"http://arxiv.org/abs/1701.08893v2","url_pdf":"http://arxiv.org/pdf/1701.08893v2.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":"stable-and-controllable-neural-texture","repo_url":"https://github.com/Asteur/paint_harmonization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"stable-and-controllable-neural-texture","repo_url":"https://github.com/chenqikkl/Qi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"stable-and-controllable-neural-texture","repo_url":"https://github.com/freedombenLiu/deep-painterly-harmonization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"stable-and-controllable-neural-texture","repo_url":"https://github.com/imransalam/style-transfer-tensorflow-2.0","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"stable-and-controllable-neural-texture","repo_url":"https://github.com/viriditass/Style-transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"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=1701.08893","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}