{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/addressing-the-generalization-of-3d","title":"Addressing the generalization of 3D registration methods with a featureless baseline and an unbiased benchmark","arxiv_id":null,"date":"2024-03-23","proceeding":"Machine Vision and Applications 2024 3","authors":["Bojanić","David; Bartol","Kristijan; Forest","Josep; Petković","Tomislav; Pribanić","Tomislav"],"abstract":"Recent 3D registration methods are mostly learning-based that either find correspondences in feature space and match them, or directly estimate the registration transformation from the given point cloud features. Therefore, these feature-based methods have difficulties with generalizing onto point clouds that differ substantially from their training data. This issue is not so apparent because of the problematic benchmark definitions that cannot provide any in-depth analysis and contain a bias toward similar data. Therefore, we propose a methodology to create a 3D registration benchmark, given a point cloud dataset, that provides a more informative evaluation of a method w.r.t. other benchmarks. Using this methodology, we create a novel FAUST-partial (FP) benchmark, based on the FAUST dataset, with several difficulty levels. The FP benchmark addresses the limitations of the current benchmarks: lack of data and parameter range variability, and allows to evaluate the strengths and weaknesses of a 3D registration method w.r.t. a single registration parameter. Using the new FP benchmark, we provide a thorough analysis of the current state-of-the-art methods and observe that the current method still struggle to generalize onto severely different out-of-sample data. Therefore, we propose a simple featureless traditional 3D registration baseline method based on the weighted cross-correlation between two given point clouds. Our method achieves strong results on current benchmarking datasets, outperforming most deep learning methods. Our source code is available on github.com/DavidBoja/exhaustive-grid-search.","url_abs":"https://link.springer.com/article/10.1007/s00138-024-01510-w","url_pdf":"https://link.springer.com/article/10.1007/s00138-024-01510-w","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":"addressing-the-generalization-of-3d","repo_url":"https://github.com/DavidBoja/exhaustive-grid-search","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"image-to-point-cloud-registration","task_name":"Image to Point Cloud Registration"},{"task_slug":"point-cloud-registration","task_name":"Point Cloud Registration"}],"methods":[],"datasets_introduced":[{"slug":"faust-partial-1","name":"FAUST-partial","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-cloud-registration-on-3dmatch-at-least-1","task":"Point Cloud Registration","dataset":"3DMatch (at least 30% overlapped - FCGF setting)","model":"Exhaustive Grid Search","rank_in_archive_order":6,"of":14,"metrics":{"Recall (0.3m, 15 degrees)":"84.11"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-eth-trained-on","task":"Point Cloud Registration","dataset":"ETH (trained on 3DMatch)","model":"Exhaustive Grid Search","rank_in_archive_order":12,"of":20,"metrics":{"Recall (30cm, 5 degrees)":"94.25"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-o-e","task":"Point Cloud Registration","dataset":"FP-O-E","model":"Exhaustive Grid Search","rank_in_archive_order":3,"of":6,"metrics":{"RRE (degrees)":"0.067","RTE (cm)":"0.035","Recall (3cm, 10 degrees)":"99.47"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-o-h","task":"Point Cloud Registration","dataset":"FP-O-H","model":"Exhaustive Grid Search","rank_in_archive_order":2,"of":6,"metrics":{"RRE (degrees)":"0.477","RTE (cm)":"0.234","Recall (3cm, 10 degrees)":"37.06"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-o-m","task":"Point Cloud Registration","dataset":"FP-O-M","model":"Exhaustive Grid Search","rank_in_archive_order":1,"of":6,"metrics":{"RRE (degrees)":"0.030","RTE (cm)":"0.017","Recall (3cm, 10 degrees)":"88.06"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-r-e","task":"Point Cloud Registration","dataset":"FP-R-E","model":"Exhaustive Grid Search","rank_in_archive_order":2,"of":6,"metrics":{"RRE (degrees)":"0.005","RTE (cm)":"0.002","Recall (3cm, 10 degrees)":"99.64"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-r-h","task":"Point Cloud Registration","dataset":"FP-R-H","model":"Exhaustive Grid Search","rank_in_archive_order":3,"of":6,"metrics":{"RRE (degrees)":"0.01","RTE (cm)":"0.007","Recall (3cm, 10 degrees)":"78.00"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-r-m","task":"Point Cloud Registration","dataset":"FP-R-M","model":"Exhaustive Grid Search","rank_in_archive_order":2,"of":6,"metrics":{"RRE (degrees)":"0.003","RTE (cm)":"0.003","Recall (3cm, 10 degrees)":"97.92"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-t-e","task":"Point Cloud Registration","dataset":"FP-T-E","model":"Exhaustive Grid Search","rank_in_archive_order":2,"of":6,"metrics":{"RRE (degrees)":"0.005","RTE (cm)":"0.002","Recall (3cm, 10 degrees)":"99.70"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-t-h","task":"Point Cloud Registration","dataset":"FP-T-H","model":"Exhaustive Grid Search","rank_in_archive_order":3,"of":6,"metrics":{"RRE (degrees)":"0.005","RTE (cm)":"0.002","Recall (3cm, 10 degrees)":"98.81"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-t-m","task":"Point Cloud Registration","dataset":"FP-T-M","model":"Exhaustive Grid Search","rank_in_archive_order":1,"of":6,"metrics":{"RRE (degrees)":"0.005","RTE (cm)":"0.002","Recall (3cm, 10 degrees)":"99.82"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-kitti-fcgf","task":"Point Cloud Registration","dataset":"KITTI (FCGF setting)","model":"Exhaustive Grid Search","rank_in_archive_order":9,"of":11,"metrics":{"Recall (0.6m, 5 degrees)":"94.59"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-kitti-trained-on","task":"Point Cloud Registration","dataset":"KITTI (trained on 3DMatch)","model":"Exhaustive Grid Search","rank_in_archive_order":4,"of":14,"metrics":{"Success Rate":"94.95"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"DavidBoja/exhaustive-grid-search","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"12ab97b28927dfeb5ff97ff631c5e189238f39d44888bb432ca42077950eca46","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}