{"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/real-time-intensity-image-reconstruction-for","title":"Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation","arxiv_id":"1607.06283","date":"2016-07-21","proceeding":null,"authors":["Christian Reinbacher","Gottfried Graber","Thomas Pock"],"abstract":"Event cameras or neuromorphic cameras mimic the human perception system as\nthey measure the per-pixel intensity change rather than the actual intensity\nlevel. In contrast to traditional cameras, such cameras capture new information\nabout the scene at MHz frequency in the form of sparse events. The high\ntemporal resolution comes at the cost of losing the familiar per-pixel\nintensity information. In this work we propose a variational model that\naccurately models the behaviour of event cameras, enabling reconstruction of\nintensity images with arbitrary frame rate in real-time. Our method is\nformulated on a per-event-basis, where we explicitly incorporate information\nabout the asynchronous nature of events via an event manifold induced by the\nrelative timestamps of events. In our experiments we verify that solving the\nvariational model on the manifold produces high-quality images without\nexplicitly estimating optical flow.","url_abs":"http://arxiv.org/abs/1607.06283v2","url_pdf":"http://arxiv.org/pdf/1607.06283v2.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":"real-time-intensity-image-reconstruction-for","repo_url":"https://github.com/VLOGroup/dvs-reconstruction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1607.06283","atlas_url":"https://app.syntology.ai/?focus=1607.06283","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}