{"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/a-style-aware-content-loss-for-real-time-hd","title":"A Style-Aware Content Loss for Real-time HD Style Transfer","arxiv_id":"1807.10201","date":"2018-07-26","proceeding":"ECCV 2018 9","authors":["Artsiom Sanakoyeu","Dmytro Kotovenko","Sabine Lang","Björn Ommer"],"abstract":"Recently, style transfer has received a lot of attention. While much of this\nresearch has aimed at speeding up processing, the approaches are still lacking\nfrom a principled, art historical standpoint: a style is more than just a\nsingle image or an artist, but previous work is limited to only a single\ninstance of a style or shows no benefit from more images. Moreover, previous\nwork has relied on a direct comparison of art in the domain of RGB images or on\nCNNs pre-trained on ImageNet, which requires millions of labeled object\nbounding boxes and can introduce an extra bias, since it has been assembled\nwithout artistic consideration. To circumvent these issues, we propose a\nstyle-aware content loss, which is trained jointly with a deep encoder-decoder\nnetwork for real-time, high-resolution stylization of images and videos. We\npropose a quantitative measure for evaluating the quality of a stylized image\nand also have art historians rank patches from our approach against those from\nprevious work. These and our qualitative results ranging from small image\npatches to megapixel stylistic images and videos show that our approach better\ncaptures the subtle nature in which a style affects content.","url_abs":"http://arxiv.org/abs/1807.10201v2","url_pdf":"http://arxiv.org/pdf/1807.10201v2.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":"a-style-aware-content-loss-for-real-time-hd","repo_url":"https://github.com/CompVis/adaptive-style-transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-style-aware-content-loss-for-real-time-hd","repo_url":"https://github.com/GuillaumeAI/rwml__adaptive_style_transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-style-aware-content-loss-for-real-time-hd","repo_url":"https://github.com/Net-Mist/style-transfer-tf2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-style-aware-content-loss-for-real-time-hd","repo_url":"https://github.com/Tonyhuiii/color-transform","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-style-aware-content-loss-for-real-time-hd","repo_url":"https://github.com/Uemuet/style-transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-style-aware-content-loss-for-real-time-hd","repo_url":"https://github.com/Uemuet/styletransfer-adaptive","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-style-aware-content-loss-for-real-time-hd","repo_url":"https://github.com/cristinecosta/CompVis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-style-aware-content-loss-for-real-time-hd","repo_url":"https://github.com/gunpowder1473/Adaptive-Style-Transfer-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-style-aware-content-loss-for-real-time-hd","repo_url":"https://github.com/sundogai/style-transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-stylization","task_name":"Image Stylization"},{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"video-style-transfer","task_name":"Video Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.10201","atlas_url":"https://app.syntology.ai/?focus=1807.10201","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}