{"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/stylebank-an-explicit-representation-for","title":"StyleBank: An Explicit Representation for Neural Image Style Transfer","arxiv_id":"1703.09210","date":"2017-03-27","proceeding":"CVPR 2017 7","authors":["Dongdong Chen","Lu Yuan","Jing Liao","Nenghai Yu","Gang Hua"],"abstract":"We propose StyleBank, which is composed of multiple convolution filter banks\nand each filter bank explicitly represents one style, for neural image style\ntransfer. To transfer an image to a specific style, the corresponding filter\nbank is operated on top of the intermediate feature embedding produced by a\nsingle auto-encoder. The StyleBank and the auto-encoder are jointly learnt,\nwhere the learning is conducted in such a way that the auto-encoder does not\nencode any style information thanks to the flexibility introduced by the\nexplicit filter bank representation. It also enables us to conduct incremental\nlearning to add a new image style by learning a new filter bank while holding\nthe auto-encoder fixed. The explicit style representation along with the\nflexible network design enables us to fuse styles at not only the image level,\nbut also the region level. Our method is the first style transfer network that\nlinks back to traditional texton mapping methods, and hence provides new\nunderstanding on neural style transfer. Our method is easy to train, runs in\nreal-time, and produces results that qualitatively better or at least\ncomparable to existing methods.","url_abs":"http://arxiv.org/abs/1703.09210v2","url_pdf":"http://arxiv.org/pdf/1703.09210v2.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":"stylebank-an-explicit-representation-for","repo_url":"https://github.com/jxcodetw/stylebank","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"stylebank-an-explicit-representation-for","repo_url":"https://github.com/yujiachen-y/StyleBank","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1703.09210","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}