{"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/semi-dense-3d-reconstruction-with-a-stereo","title":"Semi-Dense 3D Reconstruction with a Stereo Event Camera","arxiv_id":"1807.07429","date":"2018-07-19","proceeding":"ECCV 2018 9","authors":["Yi Zhou","Guillermo Gallego","Henri Rebecq","Laurent Kneip","Hongdong Li","Davide Scaramuzza"],"abstract":"Event cameras are bio-inspired sensors that offer several advantages, such as\nlow latency, high-speed and high dynamic range, to tackle challenging scenarios\nin computer vision. This paper presents a solution to the problem of 3D\nreconstruction from data captured by a stereo event-camera rig moving in a\nstatic scene, such as in the context of stereo Simultaneous Localization and\nMapping. The proposed method consists of the optimization of an energy function\ndesigned to exploit small-baseline spatio-temporal consistency of events\ntriggered across both stereo image planes. To improve the density of the\nreconstruction and to reduce the uncertainty of the estimation, a probabilistic\ndepth-fusion strategy is also developed. The resulting method has no special\nrequirements on either the motion of the stereo event-camera rig or on prior\nknowledge about the scene. Experiments demonstrate our method can deal with\nboth texture-rich scenes as well as sparse scenes, outperforming\nstate-of-the-art stereo methods based on event data image representations.","url_abs":"http://arxiv.org/abs/1807.07429v1","url_pdf":"http://arxiv.org/pdf/1807.07429v1.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":"semi-dense-3d-reconstruction-with-a-stereo","repo_url":"https://github.com/HKUST-Aerial-Robotics/ESVO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"semi-dense-3d-reconstruction-with-a-stereo","repo_url":"https://github.com/gogojjh/ESVO_extension","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"semi-dense-3d-reconstruction-with-a-stereo","repo_url":"https://github.com/nail-hnu/esvio_aa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"semi-dense-3d-reconstruction-with-a-stereo","repo_url":"https://github.com/nail-hnu/esvo2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"simultaneous-localization-and-mapping","task_name":"Simultaneous Localization and Mapping"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.07429","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}