{"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/video-acceleration-magnification","title":"Video Acceleration Magnification","arxiv_id":"1704.04186","date":"2017-04-13","proceeding":"CVPR 2017 7","authors":["Yichao Zhang","Silvia L. Pintea","Jan C. van Gemert"],"abstract":"The ability to amplify or reduce subtle image changes over time is useful in\ncontexts such as video editing, medical video analysis, product quality control\nand sports. In these contexts there is often large motion present which\nseverely distorts current video amplification methods that magnify change\nlinearly. In this work we propose a method to cope with large motions while\nstill magnifying small changes. We make the following two observations: i)\nlarge motions are linear on the temporal scale of the small changes; ii) small\nchanges deviate from this linearity. We ignore linear motion and propose to\nmagnify acceleration. Our method is pure Eulerian and does not require any\noptical flow, temporal alignment or region annotations. We link temporal\nsecond-order derivative filtering to spatial acceleration magnification. We\napply our method to moving objects where we show motion magnification and color\nmagnification. We provide quantitative as well as qualitative evidence for our\nmethod while comparing to the state-of-the-art.","url_abs":"http://arxiv.org/abs/1704.04186v2","url_pdf":"http://arxiv.org/pdf/1704.04186v2.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":"video-acceleration-magnification","repo_url":"https://github.com/acceleration-magnification/sources","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"motion-magnification","task_name":"Motion Magnification"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"video-editing","task_name":"Video Editing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.04186","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}