{"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/artistic-style-transfer-for-videos-and","title":"Artistic style transfer for videos and spherical images","arxiv_id":"1708.04538","date":"2017-08-13","proceeding":null,"authors":["Manuel Ruder","Alexey Dosovitskiy","Thomas Brox"],"abstract":"Manually re-drawing an image in a certain artistic style takes a professional\nartist a long time. Doing this for a video sequence single-handedly is beyond\nimagination. We present two computational approaches that transfer the style\nfrom one image (for example, a painting) to a whole video sequence. In our\nfirst approach, we adapt to videos the original image style transfer technique\nby Gatys et al. based on energy minimization. We introduce new ways of\ninitialization and new loss functions to generate consistent and stable\nstylized video sequences even in cases with large motion and strong occlusion.\nOur second approach formulates video stylization as a learning problem. We\npropose a deep network architecture and training procedures that allow us to\nstylize arbitrary-length videos in a consistent and stable way, and nearly in\nreal time. We show that the proposed methods clearly outperform simpler\nbaselines both qualitatively and quantitatively. Finally, we propose a way to\nadapt these approaches also to 360 degree images and videos as they emerge with\nrecent virtual reality hardware.","url_abs":"http://arxiv.org/abs/1708.04538v3","url_pdf":"http://arxiv.org/pdf/1708.04538v3.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":"artistic-style-transfer-for-videos-and","repo_url":"https://github.com/manuelruder/fast-artistic-videos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"artistic-style-transfer-for-videos-and","repo_url":"https://github.com/Kishwar/tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"artistic-style-transfer-for-videos-and","repo_url":"https://github.com/OfekCohen1/Style-On-3D-Video","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"artistic-style-transfer-for-videos-and","repo_url":"https://github.com/TanguyJeanneau/white-mirror","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.04538","atlas_url":"https://app.syntology.ai/?focus=1708.04538","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}