{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/parameter-is-not-all-you-need-starting-from","title":"Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis","arxiv_id":"2303.08134","date":"2023-03-14","proceeding":null,"authors":["Renrui Zhang","Liuhui Wang","Ziyu Guo","Yali Wang","Peng Gao","Hongsheng Li","Jianbo Shi"],"abstract":"We present a Non-parametric Network for 3D point cloud analysis, Point-NN, which consists of purely non-learnable components: farthest point sampling (FPS), k-nearest neighbors (k-NN), and pooling operations, with trigonometric functions. Surprisingly, it performs well on various 3D tasks, requiring no parameters or training, and even surpasses existing fully trained models. Starting from this basic non-parametric model, we propose two extensions. First, Point-NN can serve as a base architectural framework to construct Parametric Networks by simply inserting linear layers on top. Given the superior non-parametric foundation, the derived Point-PN exhibits a high performance-efficiency trade-off with only a few learnable parameters. Second, Point-NN can be regarded as a plug-and-play module for the already trained 3D models during inference. Point-NN captures the complementary geometric knowledge and enhances existing methods for different 3D benchmarks without re-training. We hope our work may cast a light on the community for understanding 3D point clouds with non-parametric methods. Code is available at https://github.com/ZrrSkywalker/Point-NN.","url_abs":"https://arxiv.org/abs/2303.08134v2","url_pdf":"https://arxiv.org/pdf/2303.08134v2.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":"parameter-is-not-all-you-need-starting-from","repo_url":"https://github.com/zrrskywalker/point-nn","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"parameter-is-not-all-you-need-starting-from","repo_url":"https://github.com/asalarpour/Point_GN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"parameter-is-not-all-you-need-starting-from","repo_url":"https://github.com/opengvlab/cafo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"all","task_name":"All"},{"task_slug":"supervised-only-3d-point-cloud-classification","task_name":"Supervised Only 3D Point Cloud Classification"},{"task_slug":"training-free-3d-part-segmentation","task_name":"Training-free 3D Part Segmentation"},{"task_slug":"training-free-3d-point-cloud-classification","task_name":"Training-free 3D Point Cloud Classification"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"Point-PN","rank_in_archive_order":47,"of":111,"metrics":{"Number of params":"0.8M","Overall Accuracy":"93.8"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"Point-PN","rank_in_archive_order":45,"of":77,"metrics":{"Number of params":"0.8M","Overall Accuracy":"87.1"},"uses_additional_data":false},{"leaderboard":"/sota/supervised-only-3d-point-cloud-classification","task":"Supervised Only 3D Point Cloud Classification","dataset":"ScanObjectNN","model":"Point-PN","rank_in_archive_order":7,"of":12,"metrics":{"Number of params (M)":"0.8","Overall Accuracy (PB_T50_RS)":"87.1"},"uses_additional_data":false},{"leaderboard":"/sota/training-free-3d-part-segmentation-on","task":"Training-free 3D Part Segmentation","dataset":"ShapeNet-Part","model":"Point-NN","rank_in_archive_order":1,"of":3,"metrics":{"Need 3D Data?":"Yes","Parameters":"0M","mIoU":"74.0"},"uses_additional_data":false},{"leaderboard":"/sota/training-free-3d-point-cloud-classification","task":"Training-free 3D Point Cloud Classification","dataset":"ModelNet40","model":"Point-NN","rank_in_archive_order":2,"of":7,"metrics":{"Accuracy (%)":"82.6","Need 3D Data?":"Yes","Parameters":"0M"},"uses_additional_data":false},{"leaderboard":"/sota/training-free-3d-point-cloud-classification-1","task":"Training-free 3D Point Cloud Classification","dataset":"ScanObjectNN","model":"Point-NN","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy (%)":"64.9","Need 3D Data?":"Yes","Parameters":"0M"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2303.08134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08134"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/asalarpour/Point_GN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zrrskywalker/point-nn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opengvlab/cafo","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"d035ce15cf041e94","entry":"process_data","repo":"asalarpour/Point_GN","repo_kind":"listed","path":"train_free_main.py","file_url":"https://github.com/asalarpour/Point_GN/blob/HEAD/train_free_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d035ce15cf041e94"}},{"code_sha256_prefix":"fd36ede5044ec409","entry":"normalize_tensor","repo":"asalarpour/Point_GN","repo_kind":"listed","path":"models/point_gn.py","file_url":"https://github.com/asalarpour/Point_GN/blob/HEAD/models/point_gn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fd36ede5044ec409"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}