{"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/deep-learning-for-vanishing-point-detection","title":"Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection","arxiv_id":"1707.02427","date":"2017-07-08","proceeding":null,"authors":["Florian Kluger","Hanno Ackermann","Michael Ying Yang","Bodo Rosenhahn"],"abstract":"We present a novel approach for vanishing point detection from uncalibrated\nmonocular images. In contrast to state-of-the-art, we make no a priori\nassumptions about the observed scene. Our method is based on a convolutional\nneural network (CNN) which does not use natural images, but a Gaussian sphere\nrepresentation arising from an inverse gnomonic projection of lines detected in\nan image. This allows us to rely on synthetic data for training, eliminating\nthe need for labelled images. Our method achieves competitive performance on\nthree horizon estimation benchmark datasets. We further highlight some\nadditional use cases for which our vanishing point detection algorithm can be\nused.","url_abs":"http://arxiv.org/abs/1707.02427v2","url_pdf":"http://arxiv.org/pdf/1707.02427v2.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":"deep-learning-for-vanishing-point-detection","repo_url":"https://github.com/yanconglin/vanishingpoint_houghtransform_gaussiansphere","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-learning-for-vanishing-point-detection","repo_url":"https://github.com/fkluger/Vanishing_Points_GCPR17","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"camera-calibration","task_name":"Camera Calibration"},{"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":"DL-IGP","rank_in_archive_order":3,"of":4,"metrics":{"AUC (horizon error)":"86.26"},"uses_additional_data":false},{"leaderboard":"/sota/horizon-line-estimation-on-horizon-lines-in","task":"Horizon Line Estimation","dataset":"Horizon Lines in the Wild","model":"DL-IGP","rank_in_archive_order":4,"of":5,"metrics":{"AUC (horizon error)":"57.31"},"uses_additional_data":false},{"leaderboard":"/sota/horizon-line-estimation-on-york-urban-dataset","task":"Horizon Line Estimation","dataset":"York Urban Dataset","model":"DL-IGP","rank_in_archive_order":3,"of":4,"metrics":{"AUC (horizon error)":"94.27"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.02427","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}