{"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/wxbs-wide-baseline-stereo-generalizations","title":"WxBS: Wide Baseline Stereo Generalizations","arxiv_id":"1504.06603","date":"2015-04-24","proceeding":null,"authors":["Dmytro Mishkin","Jiri Matas","Michal Perdoch","Karel Lenc"],"abstract":"We have presented a new problem -- the wide multiple baseline stereo (WxBS)\n-- which considers matching of images that simultaneously differ in more than\none image acquisition factor such as viewpoint, illumination, sensor type or\nwhere object appearance changes significantly, e.g. over time. A new dataset\nwith the ground truth for evaluation of matching algorithms has been introduced\nand will be made public.\n  We have extensively tested a large set of popular and recent detectors and\ndescriptors and show than the combination of RootSIFT and HalfRootSIFT as\ndescriptors with MSER and Hessian-Affine detectors works best for many\ndifferent nuisance factors. We show that simple adaptive thresholding improves\nHessian-Affine, DoG, MSER (and possibly other) detectors and allows to use them\non infrared and low contrast images.\n  A novel matching algorithm for addressing the WxBS problem has been\nintroduced. We have shown experimentally that the WxBS-M matcher dominantes the\nstate-of-the-art methods both on both the new and existing datasets.","url_abs":"http://arxiv.org/abs/1504.06603v2","url_pdf":"http://arxiv.org/pdf/1504.06603v2.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":"wxbs-wide-baseline-stereo-generalizations","repo_url":"https://github.com/ducha-aiki/mods","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"wxbs-wide-baseline-stereo-generalizations","repo_url":"https://github.com/ducha-aiki/wxbs-descriptors-benchmark","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=1504.06603","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}