{"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/nm-net-mining-reliable-neighbors-for-robust","title":"NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences","arxiv_id":"1904.00320","date":"2019-03-31","proceeding":"CVPR 2019 6","authors":["Chen Zhao","Zhiguo Cao","Chi Li","Xin Li","Jiaqi Yang"],"abstract":"Feature correspondence selection is pivotal to many feature-matching based\ntasks in computer vision. Searching for spatially k-nearest neighbors is a\ncommon strategy for extracting local information in many previous works.\nHowever, there is no guarantee that the spatially k-nearest neighbors of\ncorrespondences are consistent because the spatial distribution of false\ncorrespondences is often irregular. To address this issue, we present a\ncompatibility-specific mining method to search for consistent neighbors.\nMoreover, in order to extract and aggregate more reliable features from\nneighbors, we propose a hierarchical network named NM-Net with a series of\nconvolution layers taking the generated graph as input, which is insensitive to\nthe order of correspondences. Our experimental results have shown the proposed\nmethod achieves the state-of-the-art performance on four datasets with various\ninlier ratios and varying numbers of feature consistencies.","url_abs":"http://arxiv.org/abs/1904.00320v1","url_pdf":"http://arxiv.org/pdf/1904.00320v1.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":"nm-net-mining-reliable-neighbors-for-robust","repo_url":"https://github.com/sailor-z/NM-Net","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.00320","atlas_url":"https://app.syntology.ai/?focus=1904.00320","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}