{"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/enft-efficient-non-consecutive-feature","title":"ENFT: Efficient Non-Consecutive Feature Tracking for Robust Structure-from-Motion","arxiv_id":"1510.08012","date":"2015-10-27","proceeding":null,"authors":["Guofeng Zhang","Hao-Min Liu","Zilong Dong","Jiaya Jia","Tien-Tsin Wong","Hujun Bao"],"abstract":"Structure-from-motion (SfM) largely relies on feature tracking. In image\nsequences, if disjointed tracks caused by objects moving in and out of the\nfield of view, occasional occlusion, or image noise, are not handled well,\ncorresponding SfM could be affected. This problem becomes severer for\nlarge-scale scenes, which typically requires to capture multiple sequences to\ncover the whole scene. In this paper, we propose an efficient non-consecutive\nfeature tracking (ENFT) framework to match interrupted tracks distributed in\ndifferent subsequences or even in different videos. Our framework consists of\nsteps of solving the feature `dropout' problem when indistinctive structures,\nnoise or large image distortion exists, and of rapidly recognizing and joining\ncommon features located in different subsequences. In addition, we contribute\nan effective segment-based coarse-to-fine SfM algorithm for robustly handling\nlarge datasets. Experimental results on challenging video data demonstrate the\neffectiveness of the proposed system.","url_abs":"http://arxiv.org/abs/1510.08012v2","url_pdf":"http://arxiv.org/pdf/1510.08012v2.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":"enft-efficient-non-consecutive-feature","repo_url":"https://github.com/ZJUCVG/ENFT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"enft-efficient-non-consecutive-feature","repo_url":"https://github.com/ZJUCVG/ENFT-SfM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"enft-efficient-non-consecutive-feature","repo_url":"https://github.com/ZJUCVG/SegmentBA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1510.08012","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}