{"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/detecting-vanishing-points-using-global-image","title":"Detecting Vanishing Points using Global Image Context in a Non-Manhattan World","arxiv_id":"1608.05684","date":"2016-08-19","proceeding":"CVPR 2016 6","authors":["Menghua Zhai","Scott Workman","Nathan Jacobs"],"abstract":"We propose a novel method for detecting horizontal vanishing points and the\nzenith vanishing point in man-made environments. The dominant trend in existing\nmethods is to first find candidate vanishing points, then remove outliers by\nenforcing mutual orthogonality. Our method reverses this process: we propose a\nset of horizon line candidates and score each based on the vanishing points it\ncontains. A key element of our approach is the use of global image context,\nextracted with a deep convolutional network, to constrain the set of candidates\nunder consideration. Our method does not make a Manhattan-world assumption and\ncan operate effectively on scenes with only a single horizontal vanishing\npoint. We evaluate our approach on three benchmark datasets and achieve\nstate-of-the-art performance on each. In addition, our approach is\nsignificantly faster than the previous best method.","url_abs":"http://arxiv.org/abs/1608.05684v1","url_pdf":"http://arxiv.org/pdf/1608.05684v1.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":"detecting-vanishing-points-using-global-image","repo_url":"https://github.com/viibridges/gc-horizon-detector","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"horizon-line-estimation","task_name":"Horizon Line Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/horizon-line-estimation-on-eurasian-cities","task":"Horizon Line Estimation","dataset":"Eurasian Cities Dataset","model":"CNN+FULL","rank_in_archive_order":2,"of":4,"metrics":{"AUC (horizon error)":"90.80"},"uses_additional_data":false},{"leaderboard":"/sota/horizon-line-estimation-on-horizon-lines-in","task":"Horizon Line Estimation","dataset":"Horizon Lines in the Wild","model":"CNN+FULL","rank_in_archive_order":3,"of":5,"metrics":{"AUC (horizon error)":"58.24"},"uses_additional_data":false},{"leaderboard":"/sota/horizon-line-estimation-on-york-urban-dataset","task":"Horizon Line Estimation","dataset":"York Urban Dataset","model":"CNN+FULL","rank_in_archive_order":2,"of":4,"metrics":{"AUC (horizon error)":"94.78"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.05684","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}