{"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/avatar-net-multi-scale-zero-shot-style","title":"Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration","arxiv_id":"1805.03857","date":"2018-05-10","proceeding":"CVPR 2018 6","authors":["Lu Sheng","Ziyi Lin","Jing Shao","Xiaogang Wang"],"abstract":"Zero-shot artistic style transfer is an important image synthesis problem\naiming at transferring arbitrary style into content images. However, the\ntrade-off between the generalization and efficiency in existing methods impedes\na high quality zero-shot style transfer in real-time. In this paper, we resolve\nthis dilemma and propose an efficient yet effective Avatar-Net that enables\nvisually plausible multi-scale transfer for arbitrary style. The key ingredient\nof our method is a style decorator that makes up the content features by\nsemantically aligned style features from an arbitrary style image, which does\nnot only holistically match their feature distributions but also preserve\ndetailed style patterns in the decorated features. By embedding this module\ninto an image reconstruction network that fuses multi-scale style abstractions,\nthe Avatar-Net renders multi-scale stylization for any style image in one\nfeed-forward pass. We demonstrate the state-of-the-art effectiveness and\nefficiency of the proposed method in generating high-quality stylized images,\nwith a series of applications include multiple style integration, video\nstylization and etc.","url_abs":"http://arxiv.org/abs/1805.03857v2","url_pdf":"http://arxiv.org/pdf/1805.03857v2.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":"avatar-net-multi-scale-zero-shot-style","repo_url":"https://github.com/JianqiangRen/AAMS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"avatar-net-multi-scale-zero-shot-style","repo_url":"https://github.com/LucasSheng/avatar-net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"avatar-net-multi-scale-zero-shot-style","repo_url":"https://github.com/tyui592/Avatar-Net_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1805.03857","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}