{"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/rast-restorable-arbitrary-style-transfer","title":"RAST: Restorable Arbitrary Style Transfer","arxiv_id":null,"date":"2024-01-22","proceeding":"journal 2024 1","authors":["Yingnan Ma","Chenqiu Zhao","BINGRAN HUANG","Xudong Li","Anup Basu"],"abstract":"The objective of arbitrary style transfer is to apply a given artistic or photo-realistic style to a target image.\r\nAlthough current methods have shown some success in transferring style, arbitrary style transfer still has\r\nseveral issues, including content leakage. Embedding an artistic style can result in unintended changes to the\r\nimage content. This article proposes an iterative framework called Restorable Arbitrary Style Transfer (RAST)\r\nto effectively ensure content preservation and mitigate potential alterations to the content information. RAST\r\ncan transmit both content and style information through multi-restorations and balance the content-style\r\ntradeoff in stylized images using the image restoration accuracy. To ensure RAST’s effectiveness,we introduce\r\ntwo novel loss functions: multi-restoration loss and style difference loss.We also propose a new quantitative\r\nevaluation method to assess content preservation and style embedding performance. Experimental results\r\nshow that RAST outperforms state-of-the-art methods in generating stylized images that preserve content\r\nand embed style accurately.","url_abs":"https://dl.acm.org/doi/abs/10.1145/3638770","url_pdf":"https://dl.acm.org/doi/abs/10.1145/3638770","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":"rast-restorable-arbitrary-style-transfer","repo_url":"https://github.com/YingnanMa/RAST-2.0","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}