{"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/multi-image-semantic-matching-by-mining","title":"Multi-Image Semantic Matching by Mining Consistent Features","arxiv_id":"1711.07641","date":"2017-11-21","proceeding":"CVPR 2018 6","authors":["Qianqian Wang","Xiaowei Zhou","Kostas Daniilidis"],"abstract":"This work proposes a multi-image matching method to estimate semantic\ncorrespondences across multiple images. In contrast to the previous methods\nthat optimize all pairwise correspondences, the proposed method identifies and\nmatches only a sparse set of reliable features in the image collection. In this\nway, the proposed method is able to prune nonrepeatable features and also\nhighly scalable to handle thousands of images. We additionally propose a\nlow-rank constraint to ensure the geometric consistency of feature\ncorrespondences over the whole image collection. Besides the competitive\nperformance on multi-graph matching and semantic flow benchmarks, we also\ndemonstrate the applicability of the proposed method for reconstructing\nobject-class models and discovering object-class landmarks from images without\nusing any annotation.","url_abs":"http://arxiv.org/abs/1711.07641v2","url_pdf":"http://arxiv.org/pdf/1711.07641v2.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":"multi-image-semantic-matching-by-mining","repo_url":"https://github.com/qianqianwang68/multiway","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"multi-image-semantic-matching-by-mining","repo_url":"https://github.com/zju-3dv/multiway","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"graph-matching","task_name":"Graph Matching"},{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.07641","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}