{"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/density-invariant-features-for-distant-point","title":"Density-invariant Features for Distant Point Cloud Registration","arxiv_id":"2307.09788","date":"2023-07-19","proceeding":"ICCV 2023 1","authors":["Quan Liu","Hongzi Zhu","Yunsong Zhou","Hongyang Li","Shan Chang","Minyi Guo"],"abstract":"Registration of distant outdoor LiDAR point clouds is crucial to extending the 3D vision of collaborative autonomous vehicles, and yet is challenging due to small overlapping area and a huge disparity between observed point densities. In this paper, we propose Group-wise Contrastive Learning (GCL) scheme to extract density-invariant geometric features to register distant outdoor LiDAR point clouds. We mark through theoretical analysis and experiments that, contrastive positives should be independent and identically distributed (i.i.d.), in order to train densityinvariant feature extractors. We propose upon the conclusion a simple yet effective training scheme to force the feature of multiple point clouds in the same spatial location (referred to as positive groups) to be similar, which naturally avoids the sampling bias introduced by a pair of point clouds to conform with the i.i.d. principle. The resulting fully-convolutional feature extractor is more powerful and density-invariant than state-of-the-art methods, improving the registration recall of distant scenarios on KITTI and nuScenes benchmarks by 40.9% and 26.9%, respectively. Code is available at https://github.com/liuQuan98/GCL.","url_abs":"https://arxiv.org/abs/2307.09788v2","url_pdf":"https://arxiv.org/pdf/2307.09788v2.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":"density-invariant-features-for-distant-point","repo_url":"https://github.com/liuquan98/gcl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"density-invariant-features-for-distant-point","repo_url":"https://github.com/liuQuan98/GCL-KPConv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"point-cloud-registration","task_name":"Point Cloud Registration"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-cloud-registration-on-kitti-distant-pcr","task":"Point Cloud Registration","dataset":"KITTI (Distant PCR)","model":"GCL+KPConv","rank_in_archive_order":1,"of":4,"metrics":{"RR @ Loose Criterion (5°&2m), on LoKITTI":"55.4","mRR @ Normal Criterion (1.5°&0.3m)":"88.8"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-kitti-distant-pcr","task":"Point Cloud Registration","dataset":"KITTI (Distant PCR)","model":"GCL+Conv","rank_in_archive_order":2,"of":4,"metrics":{"RR @ Loose Criterion (5°&2m), on LoKITTI":"72.3","mRR @ Normal Criterion (1.5°&0.3m)":"83.5"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-rotkitti","task":"Point Cloud Registration","dataset":"RotKITTI Registration Benchmark","model":"GCL","rank_in_archive_order":5,"of":6,"metrics":{"RR@(1,0.1)":"28.8","RR@(1.5,0.3)":"40.1"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-nuscenes-distant","task":"Point Cloud Registration","dataset":"nuScenes (Distant PCR)","model":"GCL+KPConv","rank_in_archive_order":1,"of":4,"metrics":{"RR @ Loose Criterion (5°&2m), on LoNuScenes":"86.5","mRR @ Normal Criterion (1.5°&0.3m)":"71.5"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-registration-on-nuscenes-distant","task":"Point Cloud Registration","dataset":"nuScenes (Distant PCR)","model":"GCL+Conv","rank_in_archive_order":2,"of":4,"metrics":{"RR @ Loose Criterion (5°&2m), on LoNuScenes":"82.4","mRR @ Normal Criterion (1.5°&0.3m)":"70.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.09788","atlas_url":"https://app.syntology.ai/?focus=2307.09788","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":"2307.09788"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2307.09788\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2307.09788"},"call":"get_concepts_for_paper(arxiv_id=\"2307.09788\")"}],"by_repo":[{"repo":"liuquan98/gcl","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"liuQuan98/GCL-KPConv","kind":"listed","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":"1dfd7b6414105d0747135c91d779bef34a73ef7eb7eb5b94d83eb2e994aac297","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}