{"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/progressive-color-transfer-with-dense","title":"Progressive Color Transfer with Dense Semantic Correspondences","arxiv_id":"1710.00756","date":"2017-10-02","proceeding":null,"authors":["Mingming He","Jing Liao","Dong-Dong Chen","Lu Yuan","Pedro V. Sander"],"abstract":"We propose a new algorithm for color transfer between images that have\nperceptually similar semantic structures. We aim to achieve a more accurate\ncolor transfer that leverages semantically-meaningful dense correspondence\nbetween images. To accomplish this, our algorithm uses neural representations\nfor matching. Additionally, the color transfer should be spatially variant and\nglobally coherent. Therefore, our algorithm optimizes a local linear model for\ncolor transfer satisfying both local and global constraints. Our proposed\napproach jointly optimizes matching and color transfer, adopting a\ncoarse-to-fine strategy. The proposed method can be successfully extended from\none-to-one to one-to-many color transfer. The latter further addresses the\nproblem of mismatching elements of the input image. We validate our proposed\nmethod by testing it on a large variety of image content.","url_abs":"http://arxiv.org/abs/1710.00756v2","url_pdf":"http://arxiv.org/pdf/1710.00756v2.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":"progressive-color-transfer-with-dense","repo_url":"https://github.com/dev-Adrian-Vera/Second_Partial_Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"progressive-color-transfer-with-dense","repo_url":"https://github.com/hokkaido/otomo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"progressive-color-transfer-with-dense","repo_url":"https://github.com/rassilon712/Neural_Color_Transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1710.00756","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}