{"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/learning-compact-geometric-features","title":"Learning Compact Geometric Features","arxiv_id":"1709.05056","date":"2017-09-15","proceeding":"ICCV 2017 10","authors":["Marc Khoury","Qian-Yi Zhou","Vladlen Koltun"],"abstract":"We present an approach to learning features that represent the local geometry\naround a point in an unstructured point cloud. Such features play a central\nrole in geometric registration, which supports diverse applications in robotics\nand 3D vision. Current state-of-the-art local features for unstructured point\nclouds have been manually crafted and none combines the desirable properties of\nprecision, compactness, and robustness. We show that features with these\nproperties can be learned from data, by optimizing deep networks that map\nhigh-dimensional histograms into low-dimensional Euclidean spaces. The\npresented approach yields a family of features, parameterized by dimension,\nthat are both more compact and more accurate than existing descriptors.","url_abs":"http://arxiv.org/abs/1709.05056v1","url_pdf":"http://arxiv.org/pdf/1709.05056v1.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":"learning-compact-geometric-features","repo_url":"https://github.com/marckhoury/CGF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"point-cloud-registration","task_name":"Point Cloud Registration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-cloud-registration-on-eth-trained-on","task":"Point Cloud Registration","dataset":"ETH (trained on 3DMatch)","model":"CGF","rank_in_archive_order":9,"of":20,"metrics":{"Feature Matching Recall":"0.202"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.05056","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}