{"url":"/sota/training-free-3d-point-cloud-classification-1","task":{"name":"Training-free 3D Point Cloud Classification","url":"/task/training-free-3d-point-cloud-classification","note":null},"dataset":{"name":"ScanObjectNN","url":"/dataset/scanobjectnn"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Evaluation on target datasets for 3D Point Cloud Classification without any training","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy (%)","Parameters","Need 3D Data?"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy (%)":"higher","Parameters":null,"Need 3D Data?":null}},"counts":{"rows":6,"rows_with_code":6,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":4},"rows":[{"rank_in_archive_order":1,"model":"Point-GN","metrics":{"Accuracy (%)":"86.4","Need 3D Data?":"Yes","Parameters":"0M"},"uses_additional_data":false,"paper_date":"2024-12-04","paper":"/paper/point-gn-a-non-parametric-network-using","paper_url":"https://arxiv.org/abs/2412.03056v2","paper_title":"Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification","code":"https://github.com/asalarpour/Point_GN","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Point-NN","metrics":{"Accuracy (%)":"64.9","Need 3D Data?":"Yes","Parameters":"0M"},"uses_additional_data":false,"paper_date":"2023-03-14","paper":"/paper/parameter-is-not-all-you-need-starting-from","paper_url":"https://arxiv.org/abs/2303.08134v2","paper_title":"Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis","code":"https://github.com/zrrskywalker/point-nn","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":3,"model":"PointCLIP V2","metrics":{"Accuracy (%)":"35.4","Need 3D Data?":"No"},"uses_additional_data":true,"paper_date":"2022-11-21","paper":"/paper/pointclip-v2-adapting-clip-for-powerful-3d","paper_url":"https://arxiv.org/abs/2211.11682v2","paper_title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","code":"https://github.com/zrrskywalker/pointclip","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"CLIP2Point","metrics":{"Accuracy (%)":"23.2","Need 3D Data?":"Yes"},"uses_additional_data":true,"paper_date":"2022-10-03","paper":"/paper/clip2point-transfer-clip-to-point-cloud","paper_url":"https://arxiv.org/abs/2210.01055v3","paper_title":"CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training","code":"https://github.com/tyhuang0428/CLIP2Point","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"CALIP","metrics":{"Accuracy (%)":"16.9","Need 3D Data?":"No"},"uses_additional_data":true,"paper_date":"2022-09-28","paper":"/paper/calip-zero-shot-enhancement-of-clip-with","paper_url":"https://arxiv.org/abs/2209.14169v2","paper_title":"CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention","code":"https://github.com/ziyuguo99/calip","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"PointCLIP","metrics":{"Accuracy (%)":"15.4","Need 3D Data?":"No"},"uses_additional_data":true,"paper_date":"2021-12-04","paper":"/paper/pointclip-point-cloud-understanding-by-clip","paper_url":"https://arxiv.org/abs/2112.02413v1","paper_title":"PointCLIP: Point Cloud Understanding by CLIP","code":"https://github.com/zrrskywalker/pointclip","n_code_links":2,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":6,"n_unverified":8,"n_samples":14,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":6,"n_unverified":8,"n_samples":14,"n_pointer_only_licence":2,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}