{"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/generalisable-and-distinctive-3d-local-deep","title":"Learning general and distinctive 3D local deep descriptors for point cloud registration","arxiv_id":"2105.10382","date":"2021-05-21","proceeding":null,"authors":["Fabio Poiesi","Davide Boscaini"],"abstract":"An effective 3D descriptor should be invariant to different geometric transformations, such as scale and rotation, robust to occlusions and clutter, and capable of generalising to different application domains. We present a simple yet effective method to learn general and distinctive 3D local descriptors that can be used to register point clouds that are captured in different domains. Point cloud patches are extracted, canonicalised with respect to their local reference frame, and encoded into scale and rotation-invariant compact descriptors by a deep neural network that is invariant to permutations of the input points. This design is what enables our descriptors to generalise across domains. We evaluate and compare our descriptors with alternative handcrafted and deep learning-based descriptors on several indoor and outdoor datasets that are reconstructed by using both RGBD sensors and laser scanners. Our descriptors outperform most recent descriptors by a large margin in terms of generalisation, and also become the state of the art in benchmarks where training and testing are performed in the same domain.","url_abs":"https://arxiv.org/abs/2105.10382v3","url_pdf":"https://arxiv.org/pdf/2105.10382v3.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":"generalisable-and-distinctive-3d-local-deep","repo_url":"https://github.com/fabiopoiesi/gedi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-cloud-registration-on-3dmatch-trained","task":"Point Cloud Registration","dataset":"3DMatch (trained on KITTI)","model":"GeDi","rank_in_archive_order":1,"of":5,"metrics":{"Recall":"0.922"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-3dmatch-benchmark","task":"Point Cloud Registration","dataset":"3DMatch Benchmark","model":"GeDi (no code published as of May 27 2021)","rank_in_archive_order":3,"of":15,"metrics":{"Feature Matching Recall":"97.9"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-eth-trained-on","task":"Point Cloud Registration","dataset":"ETH (trained on 3DMatch)","model":"GeDi","rank_in_archive_order":1,"of":20,"metrics":{"Feature Matching Recall":"0.982","Recall (30cm, 5 degrees)":"86.54"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-o-e","task":"Point Cloud Registration","dataset":"FP-O-E","model":"GeDi","rank_in_archive_order":2,"of":6,"metrics":{"RRE (degrees)":"1.69","RTE (cm)":"1.16","Recall (3cm, 10 degrees)":"99.64"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-o-h","task":"Point Cloud Registration","dataset":"FP-O-H","model":"GeDi","rank_in_archive_order":4,"of":6,"metrics":{"RRE (degrees)":"2.56","RTE (cm)":"1.76","Recall (3cm, 10 degrees)":"8.70"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-o-m","task":"Point Cloud Registration","dataset":"FP-O-M","model":"GeDi","rank_in_archive_order":3,"of":6,"metrics":{"RRE (degrees)":"2.14","RTE (cm)":"1.45","Recall (3cm, 10 degrees)":"75.40"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-r-e","task":"Point Cloud Registration","dataset":"FP-R-E","model":"GeDi","rank_in_archive_order":1,"of":6,"metrics":{"RRE (degrees)":"1.629","RTE (cm)":"1.162","Recall (3cm, 10 degrees)":"99.76"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-r-h","task":"Point Cloud Registration","dataset":"FP-R-H","model":"GeDi","rank_in_archive_order":1,"of":6,"metrics":{"RRE (degrees)":"1.70","RTE (cm)":"1.63","Recall (3cm, 10 degrees)":"99.41"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-r-m","task":"Point Cloud Registration","dataset":"FP-R-M","model":"GeDi","rank_in_archive_order":1,"of":6,"metrics":{"RRE (degrees)":"1.66","RTE (cm)":"1.14","Recall (3cm, 10 degrees)":"99.94"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-t-e","task":"Point Cloud Registration","dataset":"FP-T-E","model":"GeDi","rank_in_archive_order":3,"of":6,"metrics":{"RRE (degrees)":"1.68","RTE (cm)":"1.16","Recall (3cm, 10 degrees)":"99.47"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-t-h","task":"Point Cloud Registration","dataset":"FP-T-H","model":"GeDi","rank_in_archive_order":1,"of":6,"metrics":{"RRE (degrees)":"1.63","RTE (cm)":"1.14","Recall (3cm, 10 degrees)":"99.70"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-fp-t-m","task":"Point Cloud Registration","dataset":"FP-T-M","model":"GeDi","rank_in_archive_order":2,"of":6,"metrics":{"RRE (degrees)":"1.65","RTE (cm)":"1.15","Recall (3cm, 10 degrees)":"99.70"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-kitti","task":"Point Cloud Registration","dataset":"KITTI","model":"GeDi","rank_in_archive_order":1,"of":6,"metrics":{"Success Rate":"99.82"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-kitti-trained-on","task":"Point Cloud Registration","dataset":"KITTI (trained on 3DMatch)","model":"GeDi","rank_in_archive_order":1,"of":14,"metrics":{"Success Rate":"98.92"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.10382","atlas_url":"https://app.syntology.ai/?focus=2105.10382","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":"2105.10382"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2105.10382\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2105.10382"},"call":"get_concepts_for_paper(arxiv_id=\"2105.10382\")"}],"by_repo":[{"repo":"fabiopoiesi/gedi","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":"2adca4af2cc5fbedbf05a11f09b9ce0be8d92c5dfcf2a5a13e111c2bfa7907bb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}