{"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/pcam-product-of-cross-attention-matrices-for","title":"PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds","arxiv_id":"2110.01269","date":"2021-10-04","proceeding":"ICCV 2021 10","authors":["Anh-Quan Cao","Gilles Puy","Alexandre Boulch","Renaud Marlet"],"abstract":"Rigid registration of point clouds with partial overlaps is a longstanding problem usually solved in two steps: (a) finding correspondences between the point clouds; (b) filtering these correspondences to keep only the most reliable ones to estimate the transformation. Recently, several deep nets have been proposed to solve these steps jointly. We built upon these works and propose PCAM: a neural network whose key element is a pointwise product of cross-attention matrices that permits to mix both low-level geometric and high-level contextual information to find point correspondences. These cross-attention matrices also permits the exchange of context information between the point clouds, at each layer, allowing the network construct better matching features within the overlapping regions. The experiments show that PCAM achieves state-of-the-art results among methods which, like us, solve steps (a) and (b) jointly via deepnets. Our code and trained models are available at https://github.com/valeoai/PCAM.","url_abs":"https://arxiv.org/abs/2110.01269v1","url_pdf":"https://arxiv.org/pdf/2110.01269v1.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":"pcam-product-of-cross-attention-matrices-for","repo_url":"https://github.com/valeoai/pcam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"point-cloud-registration","task_name":"Point Cloud Registration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-cloud-registration-on-3dlomatch-10-30","task":"Point Cloud Registration","dataset":"3DLoMatch (10-30% overlap)","model":"PCAM (reported in REGTR)","rank_in_archive_order":7,"of":13,"metrics":{"Recall ( correspondence RMSE below 0.2)":"54.9"},"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":"PCAM-Sparse (All post-processing)","rank_in_archive_order":3,"of":14,"metrics":{"RE (all)":"8.9","Recall (0.3m, 15 degrees)":"92.4","TE (all)":"0.23"},"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":"PCAM-Soft (All post-processing)","rank_in_archive_order":5,"of":14,"metrics":{"RE (all)":"9.8","Recall (0.3m, 15 degrees)":"91.3","TE (all)":"0.24"},"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":"PCAM (reported in REGTR)","rank_in_archive_order":5,"of":11,"metrics":{"Recall ( correspondence RMSE below 0.2)":"85.5"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-kitti-fcgf","task":"Point Cloud Registration","dataset":"KITTI (FCGF setting)","model":"PCAM-soft + ICP","rank_in_archive_order":4,"of":11,"metrics":{"RE (all)":"0.79","Recall (0.6m, 5 degrees)":"98","TE (all)":"0.12"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-kitti-fcgf","task":"Point Cloud Registration","dataset":"KITTI (FCGF setting)","model":"PCAM-Sparse + ICP","rank_in_archive_order":5,"of":11,"metrics":{"RE (all)":"1.04","Recall (0.6m, 5 degrees)":"97.4","TE (all)":"0.17"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-kitti-fcgf","task":"Point Cloud Registration","dataset":"KITTI (FCGF setting)","model":"PCAM - Soft","rank_in_archive_order":6,"of":11,"metrics":{"RE (all)":"1.00","Recall (0.6m, 5 degrees)":"97.2","TE (all)":"0.18"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-kitti-fcgf","task":"Point Cloud Registration","dataset":"KITTI (FCGF setting)","model":"PCAM-Sparse","rank_in_archive_order":8,"of":11,"metrics":{"RE (all)":"1.17","Recall (0.6m, 5 degrees)":"96.5","TE (all)":"0.22"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.01269","atlas_url":"https://app.syntology.ai/?focus=2110.01269","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2110.01269"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.01269\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.01269"},"call":"get_concepts_for_paper(arxiv_id=\"2110.01269\")"}],"by_repo":[{"repo":"valeoai/pcam","kind":"official","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":"0fdc3600e11b062b0b26f70f77a5d550ae5443cc6e4f638ccf2eaf72dd42bb17","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}