{"url":"/sota/3d-object-classification-on-modelnet40","task":{"name":"3D Object Classification","url":"/task/3d-object-classification","note":null},"dataset":{"name":"ModelNet40","url":"/dataset/modelnet"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"3D Object Classification is the task of predicting the class of a 3D object point cloud.  It is a voxel level prediction where each voxel is classified into a category. The popular benchmark for this task is the ModelNet dataset. The models for this task are usually evaluated with the Classification Accuracy metric.\r\n\r\nImage: [Sedaghat et al](https://arxiv.org/pdf/1604.03351v2.pdf)","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":["Classification Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Classification Accuracy":"higher"}},"counts":{"rows":7,"rows_with_code":7,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"Ours","metrics":{"Classification Accuracy":"93.6"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/exploiting-inductive-bias-in-transformer-for","paper_url":"https://arxiv.org/abs/2304.14124v1","paper_title":"Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation","code":"https://github.com/jiamang/ibt","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"G3DNet-18 MLP, Fine-Tuned, Vote","metrics":{"Classification Accuracy":"91.7"},"uses_additional_data":true,"paper_date":"2018-03-12","paper":"/paper/general-purpose-deep-point-cloud-feature","paper_url":"https://ieeexplore.ieee.org/abstract/document/8354322","paper_title":"General-Purpose Deep Point Cloud Feature Extractor","code":"https://github.com/WDot/G3DNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"CrossMoCo","metrics":{"Classification Accuracy":"91.49"},"uses_additional_data":false,"paper_date":"2023-06-08","paper":"/paper/crossmoco-multi-modal-momentum-contrastive","paper_url":"https://ieeexplore.ieee.org/abstract/document/10229841","paper_title":"CrossMoCo: Multi-modal Momentum Contrastive Learning for Point Cloud","code":"https://github.com/snehaputul/CrossMoCo","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"O-CNN(6)","metrics":{"Classification Accuracy":"89.9"},"uses_additional_data":false,"paper_date":"2017-12-05","paper":"/paper/o-cnn-octree-based-convolutional-neural","paper_url":"http://arxiv.org/abs/1712.01537v1","paper_title":"O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis","code":"https://github.com/Microsoft/O-CNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"3D-PointCapsNet","metrics":{"Classification Accuracy":"89.3"},"uses_additional_data":false,"paper_date":"2018-12-27","paper":"/paper/3d-point-capsule-networks","paper_url":"https://arxiv.org/abs/1812.10775v2","paper_title":"3D Point Capsule Networks","code":"https://github.com/yongheng1991/3D-point-capsule-networks","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"Spherical Kernel","metrics":{"Classification Accuracy":"89.3"},"uses_additional_data":false,"paper_date":"2019-09-20","paper":"/paper/spherical-kernel-for-efficient-graph","paper_url":"https://arxiv.org/abs/1909.09287v2","paper_title":"Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds","code":"https://github.com/hlei-ziyan/SPH3D-GCN","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"ECC (12 votes)","metrics":{"Classification Accuracy":"83.2"},"uses_additional_data":false,"paper_date":"2017-04-10","paper":"/paper/dynamic-edge-conditioned-filters-in","paper_url":"http://arxiv.org/abs/1704.02901v3","paper_title":"Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs","code":"https://github.com/rusty1s/pytorch_cluster","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":1,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":1,"n_unverified":12,"n_samples":13,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":1,"n_unverified":12,"n_samples":13,"n_pointer_only_licence":0,"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"}}}