{"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/visual-attribute-transfer-through-deep-image","title":"Visual Attribute Transfer through Deep Image Analogy","arxiv_id":"1705.01088","date":"2017-05-02","proceeding":null,"authors":["Jing Liao","Yuan YAO","Lu Yuan","Gang Hua","Sing Bing Kang"],"abstract":"We propose a new technique for visual attribute transfer across images that\nmay have very different appearance but have perceptually similar semantic\nstructure. By visual attribute transfer, we mean transfer of visual information\n(such as color, tone, texture, and style) from one image to another. For\nexample, one image could be that of a painting or a sketch while the other is a\nphoto of a real scene, and both depict the same type of scene.\n  Our technique finds semantically-meaningful dense correspondences between two\ninput images. To accomplish this, it adapts the notion of \"image analogy\" with\nfeatures extracted from a Deep Convolutional Neutral Network for matching; we\ncall our technique Deep Image Analogy. A coarse-to-fine strategy is used to\ncompute the nearest-neighbor field for generating the results. We validate the\neffectiveness of our proposed method in a variety of cases, including\nstyle/texture transfer, color/style swap, sketch/painting to photo, and time\nlapse.","url_abs":"http://arxiv.org/abs/1705.01088v2","url_pdf":"http://arxiv.org/pdf/1705.01088v2.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":"visual-attribute-transfer-through-deep-image","repo_url":"https://github.com/msracver/Deep-Image-Analogy","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"visual-attribute-transfer-through-deep-image","repo_url":"https://github.com/Ben-Louis/Deep-Image-Analogy-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-attribute-transfer-through-deep-image","repo_url":"https://github.com/dypromise/Deep-Image-Analogy-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-attribute-transfer-through-deep-image","repo_url":"https://github.com/factoryIO/1-simple_neural_style_transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"visual-attribute-transfer-through-deep-image","repo_url":"https://github.com/jia-yi-chen/Illumination-guided-Neural-Style-Transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.01088","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}