{"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/neighborhood-aware-geometric-encoding-network","title":"Leveraging Inlier Correspondences Proportion for Point Cloud Registration","arxiv_id":"2201.12094","date":"2022-01-28","proceeding":null,"authors":["Lifa Zhu","Haining Guan","Changwei Lin","Renmin Han"],"abstract":"In feature-learning based point cloud registration, the correct correspondence construction is vital for the subsequent transformation estimation. However, it is still a challenge to extract discriminative features from point cloud, especially when the input is partial and composed by indistinguishable surfaces (planes, smooth surfaces, etc.). As a result, the proportion of inlier correspondences that precisely match points between two unaligned point clouds is beyond satisfaction. Motivated by this, we devise several techniques to promote feature-learning based point cloud registration performance by leveraging inlier correspondences proportion: a pyramid hierarchy decoder to characterize point features in multiple scales, a consistent voting strategy to maintain consistent correspondences and a geometry guided encoding module to take geometric characteristics into consideration. Based on the above techniques, We build our Geometry-guided Consistent Network (GCNet), and challenge GCNet by indoor, outdoor and object-centric synthetic datasets. Comprehensive experiments demonstrate that GCNet outperforms the state-of-the-art methods and the techniques used in GCNet is model-agnostic, which could be easily migrated to other feature-based deep learning or traditional registration methods, and dramatically improve the performance. The code is available at https://github.com/zhulf0804/NgeNet.","url_abs":"https://arxiv.org/abs/2201.12094v2","url_pdf":"https://arxiv.org/pdf/2201.12094v2.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":"neighborhood-aware-geometric-encoding-network","repo_url":"https://github.com/zhulf0804/ngenet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"point-cloud-registration","task_name":"Point Cloud Registration"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"gcnet","method_name":"GCNet"},{"method_slug":"global-context-block","method_name":"Global Context Block"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-cloud-registration-on-3dlomatch-10-30","task":"Point Cloud Registration","dataset":"3DLoMatch (10-30% overlap)","model":"NgeNet","rank_in_archive_order":3,"of":13,"metrics":{"Recall ( correspondence RMSE below 0.2)":"71.9"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-3dmatch-at-least-1","task":"Point Cloud Registration","dataset":"3DMatch (at least 30% overlapped - FCGF setting)","model":"NgeNet","rank_in_archive_order":1,"of":14,"metrics":{"RE (all)":"4.932","Recall (0.3m, 15 degrees)":"95.0","TE (all)":"0.155"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-3dmatch-at-least-2","task":"Point Cloud Registration","dataset":"3DMatch (at least 30% overlapped - sample 5k interest points)","model":"NgeNet","rank_in_archive_order":1,"of":11,"metrics":{"Recall ( correspondence RMSE below 0.2)":"92.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.12094","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}