{"url":"/task/point-cloud-registration","name":"Point Cloud Registration","slug":"point-cloud-registration","description_markdown":"**Point Cloud Registration** is a fundamental problem in 3D computer vision and photogrammetry. Given several sets of points in different coordinate systems, the aim of registration is to find the transformation that best aligns all of them into a common coordinate system. Point Cloud Registration plays a significant role in many vision applications such as 3D model reconstruction, cultural heritage management, landslide monitoring and solar energy analysis.\r\n\r\n\r\n<span class=\"description-source\">Source: [Iterative Global Similarity Points : A robust coarse-to-fine integration solution for pairwise 3D point cloud registration ](https://arxiv.org/abs/1808.03899)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":447,"papers_with_code":229,"benchmarks":24,"benchmark_tables_in_archive":24,"benchmark_tables_shown":24,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":12,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/point-cloud-registration-on-eth-trained-on","slug":"point-cloud-registration-on-eth-trained-on","dataset":"ETH (trained on 3DMatch)","dataset_url":null,"rows_in_archive":20,"metrics":["Feature Matching Recall","Recall (30cm, 5 degrees)"],"first_row_in_archive_order":{"model":"GeDi","paper_title":"Learning general and distinctive 3D local deep descriptors for point cloud registration","paper_url":"/paper/generalisable-and-distinctive-3d-local-deep","paper_date":"2021-05-21","arxiv_id":"2105.10382","code_links":[{"title":"fabiopoiesi/gedi","url":"https://github.com/fabiopoiesi/gedi"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-3dmatch-benchmark","slug":"point-cloud-registration-on-3dmatch-benchmark","dataset":"3DMatch Benchmark","dataset_url":"/dataset/3dmatch","rows_in_archive":15,"metrics":["Feature Matching Recall"],"first_row_in_archive_order":{"model":"IMFNet","paper_title":"IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration","paper_url":"/paper/imfnet-interpretable-multimodal-fusion-for","paper_date":"2021-11-18","arxiv_id":"2111.09624","code_links":[{"title":"XiaoshuiHuang/IMFNet","url":"https://github.com/XiaoshuiHuang/IMFNet"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-3dmatch-at-least-1","slug":"point-cloud-registration-on-3dmatch-at-least-1","dataset":"3DMatch (at least 30% overlapped - FCGF setting)","dataset_url":null,"rows_in_archive":14,"metrics":["Recall (0.3m, 15 degrees)","RE (all)","TE (all)"],"first_row_in_archive_order":{"model":"NgeNet","paper_title":"Leveraging Inlier Correspondences Proportion for Point Cloud Registration","paper_url":"/paper/neighborhood-aware-geometric-encoding-network","paper_date":"2022-01-28","arxiv_id":"2201.12094","code_links":[{"title":"zhulf0804/ngenet","url":"https://github.com/zhulf0804/ngenet"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-kitti-trained-on","slug":"point-cloud-registration-on-kitti-trained-on","dataset":"KITTI (trained on 3DMatch)","dataset_url":"/dataset/kitti","rows_in_archive":14,"metrics":["Success Rate"],"first_row_in_archive_order":{"model":"GeDi","paper_title":"Learning general and distinctive 3D local deep descriptors for point cloud registration","paper_url":"/paper/generalisable-and-distinctive-3d-local-deep","paper_date":"2021-05-21","arxiv_id":"2105.10382","code_links":[{"title":"fabiopoiesi/gedi","url":"https://github.com/fabiopoiesi/gedi"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-3dlomatch-10-30","slug":"point-cloud-registration-on-3dlomatch-10-30","dataset":"3DLoMatch (10-30% overlap)","dataset_url":null,"rows_in_archive":13,"metrics":["Recall ( correspondence RMSE below 0.2)"],"first_row_in_archive_order":{"model":"CoFF","paper_title":"Cross-modal feature fusion for robust point cloud registration with ambiguous geometry","paper_url":"/paper/cross-modal-feature-fusion-for-robust-point","paper_date":"2025-05-19","arxiv_id":"2505.13088","code_links":[{"title":"zhaoyiww/coff","url":"https://github.com/zhaoyiww/coff"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-3dmatch-at-least-2","slug":"point-cloud-registration-on-3dmatch-at-least-2","dataset":"3DMatch (at least 30% overlapped - sample 5k interest points)","dataset_url":null,"rows_in_archive":11,"metrics":["Recall ( correspondence RMSE below 0.2)"],"first_row_in_archive_order":{"model":"NgeNet","paper_title":"Leveraging Inlier Correspondences Proportion for Point Cloud Registration","paper_url":"/paper/neighborhood-aware-geometric-encoding-network","paper_date":"2022-01-28","arxiv_id":"2201.12094","code_links":[{"title":"zhulf0804/ngenet","url":"https://github.com/zhulf0804/ngenet"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-kitti-fcgf","slug":"point-cloud-registration-on-kitti-fcgf","dataset":"KITTI (FCGF setting)","dataset_url":"/dataset/kitti","rows_in_archive":11,"metrics":["Recall (0.6m, 5 degrees)","RE (all)","TE (all)"],"first_row_in_archive_order":{"model":"GeoTransformer","paper_title":"Geometric Transformer for Fast and Robust Point Cloud Registration","paper_url":"/paper/geometric-transformer-for-fast-and-robust","paper_date":"2022-02-14","arxiv_id":"2202.06688","code_links":[{"title":"qinzheng93/geotransformer","url":"https://github.com/qinzheng93/geotransformer"},{"title":"weitong8591/differentiable_ransac","url":"https://github.com/weitong8591/differentiable_ransac"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":9}}},{"leaderboard":"/sota/point-cloud-registration-on-fpv1","slug":"point-cloud-registration-on-fpv1","dataset":"FPv1","dataset_url":"/dataset/faust-partial","rows_in_archive":8,"metrics":["Recall (3cm, 10 degrees)","RRE (degrees)","RTE (cm)"],"first_row_in_archive_order":{"model":"Greedy Grid Search","paper_title":"Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration","paper_url":"/paper/challenging-the-universal-representation-of","paper_date":"2022-11-29","arxiv_id":"2211.16301","code_links":[{"title":"davidboja/greedy-grid-search","url":"https://github.com/davidboja/greedy-grid-search"},{"title":"DavidBoja/FAUST-partial","url":"https://github.com/DavidBoja/FAUST-partial"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-fp-o-e","slug":"point-cloud-registration-on-fp-o-e","dataset":"FP-O-E","dataset_url":"/dataset/faust-partial-1","rows_in_archive":6,"metrics":["Recall (3cm, 10 degrees)","RRE (degrees)","RTE (cm)"],"first_row_in_archive_order":{"model":"FPFH+SC2-PCR","paper_title":"SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration","paper_url":"/paper/sc2-pcr-a-second-order-spatial-compatibility","paper_date":"2022-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-fp-o-h","slug":"point-cloud-registration-on-fp-o-h","dataset":"FP-O-H","dataset_url":"/dataset/faust-partial-1","rows_in_archive":6,"metrics":["Recall (3cm, 10 degrees)","RRE (degrees)","RTE (cm)"],"first_row_in_archive_order":{"model":"FPFH+SC2-PCR","paper_title":"SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration","paper_url":"/paper/sc2-pcr-a-second-order-spatial-compatibility","paper_date":"2022-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-fp-o-m","slug":"point-cloud-registration-on-fp-o-m","dataset":"FP-O-M","dataset_url":"/dataset/faust-partial-1","rows_in_archive":6,"metrics":["Recall (3cm, 10 degrees)","RRE (degrees)","RTE (cm)"],"first_row_in_archive_order":{"model":"Exhaustive Grid Search","paper_title":"Addressing the generalization of 3D registration methods with a featureless baseline and an unbiased benchmark","paper_url":"/paper/addressing-the-generalization-of-3d","paper_date":"2024-03-23","arxiv_id":null,"code_links":[{"title":"DavidBoja/exhaustive-grid-search","url":"https://github.com/DavidBoja/exhaustive-grid-search"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-fp-r-e","slug":"point-cloud-registration-on-fp-r-e","dataset":"FP-R-E","dataset_url":"/dataset/faust-partial-1","rows_in_archive":6,"metrics":["Recall (3cm, 10 degrees)","RRE (degrees)","RTE (cm)"],"first_row_in_archive_order":{"model":"GeDi","paper_title":"Learning general and distinctive 3D local deep descriptors for point cloud registration","paper_url":"/paper/generalisable-and-distinctive-3d-local-deep","paper_date":"2021-05-21","arxiv_id":"2105.10382","code_links":[{"title":"fabiopoiesi/gedi","url":"https://github.com/fabiopoiesi/gedi"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-fp-r-h","slug":"point-cloud-registration-on-fp-r-h","dataset":"FP-R-H","dataset_url":"/dataset/faust-partial-1","rows_in_archive":6,"metrics":["Recall (3cm, 10 degrees)","RRE (degrees)","RTE (cm)"],"first_row_in_archive_order":{"model":"GeDi","paper_title":"Learning general and distinctive 3D local deep descriptors for point cloud registration","paper_url":"/paper/generalisable-and-distinctive-3d-local-deep","paper_date":"2021-05-21","arxiv_id":"2105.10382","code_links":[{"title":"fabiopoiesi/gedi","url":"https://github.com/fabiopoiesi/gedi"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-fp-r-m","slug":"point-cloud-registration-on-fp-r-m","dataset":"FP-R-M","dataset_url":"/dataset/faust-partial-1","rows_in_archive":6,"metrics":["Recall (3cm, 10 degrees)","RRE (degrees)","RTE (cm)"],"first_row_in_archive_order":{"model":"GeDi","paper_title":"Learning general and distinctive 3D local deep descriptors for point cloud registration","paper_url":"/paper/generalisable-and-distinctive-3d-local-deep","paper_date":"2021-05-21","arxiv_id":"2105.10382","code_links":[{"title":"fabiopoiesi/gedi","url":"https://github.com/fabiopoiesi/gedi"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-fp-t-e","slug":"point-cloud-registration-on-fp-t-e","dataset":"FP-T-E","dataset_url":"/dataset/faust-partial-1","rows_in_archive":6,"metrics":["Recall (3cm, 10 degrees)","RRE (degrees)","RTE (cm)"],"first_row_in_archive_order":{"model":"FPFH+SC2-PCR","paper_title":"SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration","paper_url":"/paper/sc2-pcr-a-second-order-spatial-compatibility","paper_date":"2022-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-fp-t-h","slug":"point-cloud-registration-on-fp-t-h","dataset":"FP-T-H","dataset_url":"/dataset/faust-partial-1","rows_in_archive":6,"metrics":["Recall (3cm, 10 degrees)","RRE (degrees)","RTE (cm)"],"first_row_in_archive_order":{"model":"GeDi","paper_title":"Learning general and distinctive 3D local deep descriptors for point cloud registration","paper_url":"/paper/generalisable-and-distinctive-3d-local-deep","paper_date":"2021-05-21","arxiv_id":"2105.10382","code_links":[{"title":"fabiopoiesi/gedi","url":"https://github.com/fabiopoiesi/gedi"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-fp-t-m","slug":"point-cloud-registration-on-fp-t-m","dataset":"FP-T-M","dataset_url":"/dataset/faust-partial-1","rows_in_archive":6,"metrics":["Recall (3cm, 10 degrees)","RRE (degrees)","RTE (cm)"],"first_row_in_archive_order":{"model":"Exhaustive Grid Search","paper_title":"Addressing the generalization of 3D registration methods with a featureless baseline and an unbiased benchmark","paper_url":"/paper/addressing-the-generalization-of-3d","paper_date":"2024-03-23","arxiv_id":null,"code_links":[{"title":"DavidBoja/exhaustive-grid-search","url":"https://github.com/DavidBoja/exhaustive-grid-search"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-kitti","slug":"point-cloud-registration-on-kitti","dataset":"KITTI","dataset_url":"/dataset/kitti","rows_in_archive":6,"metrics":["Success Rate"],"first_row_in_archive_order":{"model":"GeDi","paper_title":"Learning general and distinctive 3D local deep descriptors for point cloud registration","paper_url":"/paper/generalisable-and-distinctive-3d-local-deep","paper_date":"2021-05-21","arxiv_id":"2105.10382","code_links":[{"title":"fabiopoiesi/gedi","url":"https://github.com/fabiopoiesi/gedi"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-rotkitti","slug":"point-cloud-registration-on-rotkitti","dataset":"RotKITTI Registration Benchmark","dataset_url":null,"rows_in_archive":6,"metrics":["RR@(1.5,0.3)","RR@(1,0.1)"],"first_row_in_archive_order":{"model":"UMERegRobust","paper_title":"UMERegRobust -- Universal Manifold Embedding Compatible Features for Robust Point Cloud Registration","paper_url":"/paper/umeregrobust-universal-manifold-embedding","paper_date":"2024-08-22","arxiv_id":"2408.12380","code_links":[{"title":"yuvalh9/umeregrobust","url":"https://github.com/yuvalh9/umeregrobust"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-3dmatch-trained","slug":"point-cloud-registration-on-3dmatch-trained","dataset":"3DMatch (trained on KITTI)","dataset_url":null,"rows_in_archive":5,"metrics":["Recall"],"first_row_in_archive_order":{"model":"GeDi","paper_title":"Learning general and distinctive 3D local deep descriptors for point cloud registration","paper_url":"/paper/generalisable-and-distinctive-3d-local-deep","paper_date":"2021-05-21","arxiv_id":"2105.10382","code_links":[{"title":"fabiopoiesi/gedi","url":"https://github.com/fabiopoiesi/gedi"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-kitti-distant-pcr","slug":"point-cloud-registration-on-kitti-distant-pcr","dataset":"KITTI (Distant PCR)","dataset_url":null,"rows_in_archive":4,"metrics":["mRR @ Normal Criterion (1.5°&0.3m)","RR @ Loose Criterion (5°&2m), on LoKITTI"],"first_row_in_archive_order":{"model":"GCL+KPConv","paper_title":"Density-invariant Features for Distant Point Cloud Registration","paper_url":"/paper/density-invariant-features-for-distant-point","paper_date":"2023-07-19","arxiv_id":"2307.09788","code_links":[{"title":"liuquan98/gcl","url":"https://github.com/liuquan98/gcl"},{"title":"liuQuan98/GCL-KPConv","url":"https://github.com/liuQuan98/GCL-KPConv"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-nuscenes-distant","slug":"point-cloud-registration-on-nuscenes-distant","dataset":"nuScenes (Distant PCR)","dataset_url":null,"rows_in_archive":4,"metrics":["mRR @ Normal Criterion (1.5°&0.3m)","RR @ Loose Criterion (5°&2m), on LoNuScenes"],"first_row_in_archive_order":{"model":"GCL+KPConv","paper_title":"Density-invariant Features for Distant Point Cloud Registration","paper_url":"/paper/density-invariant-features-for-distant-point","paper_date":"2023-07-19","arxiv_id":"2307.09788","code_links":[{"title":"liuquan98/gcl","url":"https://github.com/liuquan98/gcl"},{"title":"liuQuan98/GCL-KPConv","url":"https://github.com/liuQuan98/GCL-KPConv"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-scannet-trained","slug":"point-cloud-registration-on-scannet-trained","dataset":"ScanNet++ (trained on 3DMatch)","dataset_url":"/dataset/scannet-1","rows_in_archive":3,"metrics":["Recall ( correspondence RMSE below 0.2)"],"first_row_in_archive_order":{"model":"CoFF","paper_title":"Cross-modal feature fusion for robust point cloud registration with ambiguous geometry","paper_url":"/paper/cross-modal-feature-fusion-for-robust-point","paper_date":"2025-05-19","arxiv_id":"2505.13088","code_links":[{"title":"zhaoyiww/coff","url":"https://github.com/zhaoyiww/coff"}],"syntology":null}},{"leaderboard":"/sota/point-cloud-registration-on-3rscan","slug":"point-cloud-registration-on-3rscan","dataset":"3RScan","dataset_url":"/dataset/3r-scan","rows_in_archive":2,"metrics":["CD","RRE","RTE"],"first_row_in_archive_order":{"model":"SG-PGM","paper_title":"SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks","paper_url":"/paper/sg-pgm-partial-graph-matching-network-with","paper_date":"2024-03-28","arxiv_id":"2403.19474","code_links":[{"title":"dfki-av/sg-pgm","url":"https://github.com/dfki-av/sg-pgm"}],"syntology":null}}],"datasets":[{"url":"/dataset/kitti","name":"KITTI","full_name":"","num_papers_in_archive":3661},{"url":"/dataset/3dmatch","name":"3DMatch","full_name":"","num_papers_in_archive":175},{"url":"/dataset/3r-scan","name":"3RScan","full_name":"","num_papers_in_archive":44},{"url":"/dataset/deformingthings4d","name":"DeformingThings4D","full_name":"","num_papers_in_archive":42},{"url":"/dataset/scannet-1","name":"ScanNet++","full_name":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","num_papers_in_archive":25},{"url":"/dataset/urbanloco","name":"UrbanLoco","full_name":"","num_papers_in_archive":14},{"url":"/dataset/4dmatch","name":"4DMatch","full_name":"","num_papers_in_archive":10},{"url":"/dataset/3dcsr-dataset","name":"3DCSR dataset","full_name":"3D cross-source point cloud registration dataset","num_papers_in_archive":8},{"url":"/dataset/faust-partial","name":"FPv1","full_name":"","num_papers_in_archive":7},{"url":"/dataset/faust-partial-1","name":"FAUST-partial","full_name":"","num_papers_in_archive":5},{"url":"/dataset/vbr","name":"VBR","full_name":"VBR: A Vision Benchmark in Rome","num_papers_in_archive":3},{"url":"/dataset/codd","name":"CODD","full_name":"Cooperative Driving Dataset","num_papers_in_archive":1}],"subtasks":[{"url":"/task/image-to-point-cloud-registration","name":"Image to Point Cloud Registration"}],"parent_tasks":[{"url":"/task/3d-point-cloud-interpolation","name":"3D Point Cloud Interpolation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":229,"tagged_in_all":447,"items":[{"url":"/paper/open3d-a-modern-library-for-3d-data","title":"Open3D: A Modern Library for 3D Data Processing","date":"2018-01-30","arxiv_id":"1801.09847","repositories_listed":14,"syntology":null},{"url":"/paper/spinenet-learning-scale-permuted-backbone-for","title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","date":"2019-12-10","arxiv_id":"1912.05027","repositories_listed":13,"syntology":null},{"url":"/paper/teaser-fast-and-certifiable-point-cloud","title":"TEASER: Fast and Certifiable Point Cloud Registration","date":"2020-01-21","arxiv_id":"2001.07715","repositories_listed":7,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":2}},{"url":"/paper/pointnetlk-robust-efficient-point-cloud","title":"PointNetLK: Robust & Efficient Point Cloud Registration using PointNet","date":"2019-03-13","arxiv_id":"1903.05711","repositories_listed":7,"syntology":{"n":24,"n_ran":2,"n_unverified":22,"n_pointer_only":22}},{"url":"/paper/predator-registration-of-3d-point-clouds-with","title":"PREDATOR: Registration of 3D Point Clouds with Low Overlap","date":"2020-11-25","arxiv_id":"2011.13005","repositories_listed":5,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/2003-13479","title":"RPM-Net: Robust Point Matching using Learned Features","date":"2020-03-30","arxiv_id":"2003.13479","repositories_listed":5,"syntology":{"n":31,"n_ran":6,"n_unverified":25,"n_pointer_only":14}},{"url":"/paper/190807906","title":"PCRNet: Point Cloud Registration Network using PointNet Encoding","date":"2019-08-21","arxiv_id":"1908.07906","repositories_listed":5,"syntology":null},{"url":"/paper/model-free-vehicle-tracking-and-state","title":"Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences","date":"2021-03-10","arxiv_id":"2103.06028","repositories_listed":4,"syntology":null},{"url":"/paper/prnet-self-supervised-learning-for-partial-to","title":"PRNet: Self-Supervised Learning for Partial-to-Partial Registration","date":"2019-10-27","arxiv_id":"1910.12240","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/190503304","title":"Deep Closest Point: Learning Representations for Point Cloud Registration","date":"2019-05-08","arxiv_id":"1905.03304","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/lie-neurons-adjoint-equivariant-neural","title":"Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras","date":"2023-10-06","arxiv_id":"2310.04521","repositories_listed":3,"syntology":null},{"url":"/paper/pare-net-position-aware-rotation-equivariant","title":"PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration","date":"2024-07-14","arxiv_id":"2407.10142","repositories_listed":2,"syntology":null},{"url":"/paper/nerf-supervised-feature-point-detection-and","title":"NeRF-Supervised Feature Point Detection and Description","date":"2024-03-13","arxiv_id":"2403.08156","repositories_listed":2,"syntology":null},{"url":"/paper/pyramid-semantic-graph-based-global-point","title":"Pyramid Semantic Graph-based Global Point Cloud Registration with Low Overlap","date":"2023-07-22","arxiv_id":"2307.12116","repositories_listed":2,"syntology":null},{"url":"/paper/density-invariant-features-for-distant-point","title":"Density-invariant Features for Distant Point Cloud Registration","date":"2023-07-19","arxiv_id":"2307.09788","repositories_listed":2,"syntology":null},{"url":"/paper/silk-simple-learned-keypoints","title":"SiLK -- Simple Learned Keypoints","date":"2023-04-12","arxiv_id":"2304.06194","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/fully-differentiable-ransac","title":"Generalized Differentiable RANSAC","date":"2022-12-26","arxiv_id":"2212.13185","repositories_listed":2,"syntology":null},{"url":"/paper/sliced-optimal-partial-transport","title":"Sliced Optimal Partial Transport","date":"2022-12-15","arxiv_id":"2212.08049","repositories_listed":2,"syntology":null},{"url":"/paper/challenging-the-universal-representation-of","title":"Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration","date":"2022-11-29","arxiv_id":"2211.16301","repositories_listed":2,"syntology":null},{"url":"/paper/geometric-transformer-for-fast-and-robust","title":"Geometric Transformer for Fast and Robust Point Cloud Registration","date":"2022-02-14","arxiv_id":"2202.06688","repositories_listed":2,"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":9}},{"url":"/paper/multi-view-partial-mvp-point-cloud-challenge","title":"Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results","date":"2021-12-22","arxiv_id":"2112.12053","repositories_listed":2,"syntology":{"n":16,"n_ran":5,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/accurate-point-cloud-registration-with-robust","title":"Accurate Point Cloud Registration with Robust Optimal Transport","date":"2021-11-01","arxiv_id":"2111.00648","repositories_listed":2,"syntology":null},{"url":"/paper/finet-dual-branches-feature-interaction-for","title":"FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration","date":"2021-06-07","arxiv_id":"2106.03479","repositories_listed":2,"syntology":null},{"url":"/paper/reagent-point-cloud-registration-using","title":"ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning","date":"2021-03-28","arxiv_id":"2103.15231","repositories_listed":2,"syntology":null},{"url":"/paper/robust-point-cloud-registration-framework","title":"Robust Point Cloud Registration Framework Based on Deep Graph Matching","date":"2021-03-07","arxiv_id":"2103.04256","repositories_listed":2,"syntology":{"n":38,"n_ran":25,"n_unverified":13,"n_pointer_only":38}},{"url":"/paper/self-supervised-geometric-perception","title":"Self-supervised Geometric Perception","date":"2021-03-04","arxiv_id":"2103.03114","repositories_listed":2,"syntology":null},{"url":"/paper/clipper-a-graph-theoretic-framework-for","title":"CLIPPER: A Graph-Theoretic Framework for Robust Data Association","date":"2020-11-20","arxiv_id":"2011.10202","repositories_listed":2,"syntology":null},{"url":"/paper/masknet-a-fully-convolutional-network-to","title":"MaskNet: A Fully-Convolutional Network to Estimate Inlier Points","date":"2020-10-19","arxiv_id":"2010.09185","repositories_listed":2,"syntology":null},{"url":"/paper/distinctive-3d-local-deep-descriptors","title":"Distinctive 3D local deep descriptors","date":"2020-09-01","arxiv_id":"2009.00258","repositories_listed":2,"syntology":null},{"url":"/paper/deepgmr-learning-latent-gaussian-mixture","title":"DeepGMR: Learning Latent Gaussian Mixture Models for Registration","date":"2020-08-20","arxiv_id":"2008.09088","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":11,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}