{"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/large-scale-evaluation-of-local-image-feature","title":"Large scale evaluation of local image feature detectors on homography datasets","arxiv_id":"1807.07939","date":"2018-07-20","proceeding":null,"authors":["Karel Lenc","Andrea Vedaldi"],"abstract":"We present a large scale benchmark for the evaluation of local feature\ndetectors. Our key innovation is the introduction of a new evaluation protocol\nwhich extends and improves the standard detection repeatability measure. The\nnew protocol is better for assessment on a large number of images and reduces\nthe dependency of the results on unwanted distractors such as the number of\ndetected features and the feature magnification factor. Additionally, our\nprotocol provides a comprehensive assessment of the expected performance of\ndetectors under several practical scenarios. Using images from the\nrecently-introduced HPatches dataset, we evaluate a range of state-of-the-art\nlocal feature detectors on two main tasks: viewpoint and illumination invariant\ndetection. Contrary to previous detector evaluations, our study contains an\norder of magnitude more image sequences, resulting in a quantitative evaluation\nsignificantly more robust to over-fitting. We also show that traditional\ndetectors are still very competitive when compared to recent deep-learning\nalternatives.","url_abs":"http://arxiv.org/abs/1807.07939v1","url_pdf":"http://arxiv.org/pdf/1807.07939v1.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":"large-scale-evaluation-of-local-image-feature","repo_url":"https://github.com/lenck/vlb-deteval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}