{"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/neural-abstract-style-transfer-for-chinese","title":"Neural Abstract Style Transfer for Chinese Traditional Painting","arxiv_id":"1812.03264","date":"2018-12-08","proceeding":null,"authors":["Bo Li","Caiming Xiong","Tianfu Wu","Yu Zhou","Lun Zhang","Rufeng Chu"],"abstract":"Chinese traditional painting is one of the most historical artworks in the\nworld. It is very popular in Eastern and Southeast Asia due to being\naesthetically appealing. Compared with western artistic painting, it is usually\nmore visually abstract and textureless. Recently, neural network based style\ntransfer methods have shown promising and appealing results which are mainly\nfocused on western painting. It remains a challenging problem to preserve\nabstraction in neural style transfer. In this paper, we present a Neural\nAbstract Style Transfer method for Chinese traditional painting. It learns to\npreserve abstraction and other style jointly end-to-end via a novel\nMXDoG-guided filter (Modified version of the eXtended Difference-of-Gaussians)\nand three fully differentiable loss terms. To the best of our knowledge, there\nis little work study on neural style transfer of Chinese traditional painting.\nTo promote research on this direction, we collect a new dataset with diverse\nphoto-realistic images and Chinese traditional paintings. In experiments, the\nproposed method shows more appealing stylized results in transferring the style\nof Chinese traditional painting than state-of-the-art neural style transfer\nmethods.","url_abs":"http://arxiv.org/abs/1812.03264v2","url_pdf":"http://arxiv.org/pdf/1812.03264v2.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":"neural-abstract-style-transfer-for-chinese","repo_url":"https://github.com/lbsswu/Chinese_style_transfer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[{"slug":"chinese-traditional-painting-dataset","name":"Chinese Traditional Painting dataset","full_name":null}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}