{"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/learning-based-video-motion-magnification","title":"Learning-based Video Motion Magnification","arxiv_id":"1804.02684","date":"2018-04-08","proceeding":"ECCV 2018 9","authors":["Tae-Hyun Oh","Ronnachai Jaroensri","Changil Kim","Mohamed Elgharib","Frédo Durand","William T. Freeman","Wojciech Matusik"],"abstract":"Video motion magnification techniques allow us to see small motions\npreviously invisible to the naked eyes, such as those of vibrating airplane\nwings, or swaying buildings under the influence of the wind. Because the motion\nis small, the magnification results are prone to noise or excessive blurring.\nThe state of the art relies on hand-designed filters to extract representations\nthat may not be optimal. In this paper, we seek to learn the filters directly\nfrom examples using deep convolutional neural networks. To make training\ntractable, we carefully design a synthetic dataset that captures small motion\nwell, and use two-frame input for training. We show that the learned filters\nachieve high-quality results on real videos, with less ringing artifacts and\nbetter noise characteristics than previous methods. While our model is not\ntrained with temporal filters, we found that the temporal filters can be used\nwith our extracted representations up to a moderate magnification, enabling a\nfrequency-based motion selection. Finally, we analyze the learned filters and\nshow that they behave similarly to the derivative filters used in previous\nworks. Our code, trained model, and datasets will be available online.","url_abs":"http://arxiv.org/abs/1804.02684v3","url_pdf":"http://arxiv.org/pdf/1804.02684v3.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":"learning-based-video-motion-magnification","repo_url":"https://github.com/12dmodel/deep_motion_mag","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-based-video-motion-magnification","repo_url":"https://github.com/ZhengPeng7/motion_magnification_learning-based","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"motion-magnification","task_name":"Motion Magnification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.02684","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}