{"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/robust-sfm-with-little-image-overlap","title":"Robust SfM with Little Image Overlap","arxiv_id":"1703.07957","date":"2017-03-23","proceeding":null,"authors":["Yohann Salaun","Renaud Marlet","Pascal Monasse"],"abstract":"Usual Structure-from-Motion (SfM) techniques require at least trifocal\noverlaps to calibrate cameras and reconstruct a scene. We consider here\nscenarios of reduced image sets with little overlap, possibly as low as two\nimages at most seeing the same part of the scene. We propose a new method,\nbased on line coplanarity hypotheses, for estimating the relative scale of two\nindependent bifocal calibrations sharing a camera, without the need of any\ntrifocal information or Manhattan-world assumption. We use it to compute SfM in\na chain of up-to-scale relative motions. For accuracy, we however also make use\nof trifocal information for line and/or point features, when present, relaxing\nusual trifocal constraints. For robustness to wrong assumptions and mismatches,\nwe embed all constraints in a parameterless RANSAC-like approach. Experiments\nshow that we can calibrate datasets that previously could not, and that this\nwider applicability does not come at the cost of inaccuracy.","url_abs":"http://arxiv.org/abs/1703.07957v2","url_pdf":"http://arxiv.org/pdf/1703.07957v2.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":"robust-sfm-with-little-image-overlap","repo_url":"https://github.com/ySalaun/LineSfM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}