{"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/bringing-a-blurry-frame-alive-at-high-frame","title":"Bringing a Blurry Frame Alive at High Frame-Rate with an Event Camera","arxiv_id":"1811.10180","date":"2018-11-26","proceeding":"CVPR 2019 6","authors":["Liyuan Pan","Cedric Scheerlinck","Xin Yu","Richard Hartley","Miaomiao Liu","Yuchao Dai"],"abstract":"Event-based cameras can measure intensity changes (called `{\\it events}')\nwith microsecond accuracy under high-speed motion and challenging lighting\nconditions. With the active pixel sensor (APS), the event camera allows\nsimultaneous output of the intensity frames. However, the output images are\ncaptured at a relatively low frame-rate and often suffer from motion blur. A\nblurry image can be regarded as the integral of a sequence of latent images,\nwhile the events indicate the changes between the latent images. Therefore, we\nare able to model the blur-generation process by associating event data to a\nlatent image. In this paper, we propose a simple and effective approach, the\n\\textbf{Event-based Double Integral (EDI)} model, to reconstruct a high\nframe-rate, sharp video from a single blurry frame and its event data. The\nvideo generation is based on solving a simple non-convex optimization problem\nin a single scalar variable. Experimental results on both synthetic and real\nimages demonstrate the superiority of our EDI model and optimization method in\ncomparison to the state-of-the-art.","url_abs":"http://arxiv.org/abs/1811.10180v2","url_pdf":"http://arxiv.org/pdf/1811.10180v2.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":"bringing-a-blurry-frame-alive-at-high-frame","repo_url":"https://github.com/panpanfei/Bringing-a-Blurry-Frame-Alive-at-High-Frame-Rate-with-an-Event-Camera","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.10180","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}