{"url":"/sota/3d-object-recognition-on-modelnet40","task":{"name":"3D Object Recognition","url":"/task/3d-object-recognition","note":null},"dataset":{"name":"ModelNet40","url":"/dataset/modelnet"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"3D object recognition is the task of recognising objects from 3D data.\r\n\r\nNote that there are related tasks you can look at, such as [3D Object Detection](https://paperswithcode.com/task/3d-object-detection) which have more leaderboards.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">(Image credit: [Look Further to Recognize Better](https://arxiv.org/pdf/1907.12924v1.pdf))</span>","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"],"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"}},"counts":{"rows":6,"rows_with_code":6,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"R2-MLP-36","metrics":{"Accuracy":"97.7%"},"uses_additional_data":false,"paper_date":"2022-11-20","paper":"/paper/r2-mlp-round-roll-mlp-for-multi-view-3d","paper_url":"https://arxiv.org/abs/2211.11085v1","paper_title":"R2-MLP: Round-Roll MLP for Multi-View 3D Object Recognition","code":"https://github.com/shanshuo/MVT","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"MVT-small","metrics":{"Accuracy":"97.5%"},"uses_additional_data":false,"paper_date":"2021-10-25","paper":"/paper/mvt-multi-view-vision-transformer-for-3d","paper_url":"https://arxiv.org/abs/2110.13083v1","paper_title":"MVT: Multi-view Vision Transformer for 3D Object Recognition","code":"https://github.com/shanshuo/MVT","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":3,"model":"MVCNN-MultiRes","metrics":{"Accuracy":"93.8%"},"uses_additional_data":false,"paper_date":"2016-04-12","paper":"/paper/volumetric-and-multi-view-cnns-for-object","paper_url":"http://arxiv.org/abs/1604.03265v2","paper_title":"Volumetric and Multi-View CNNs for Object Classification on 3D Data","code":"https://github.com/charlesq34/3dcnn.torch","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"MeshWalker (ours)","metrics":{"Accuracy":"92.3%"},"uses_additional_data":false,"paper_date":"2020-06-09","paper":"/paper/meshwalker-deep-mesh-understanding-by-random","paper_url":"https://arxiv.org/abs/2006.05353v3","paper_title":"MeshWalker: Deep Mesh Understanding by Random Walks","code":"https://github.com/AlonLahav/MeshWalker","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"FPNN (4-FCs + NF)","metrics":{"Accuracy":"88.4%"},"uses_additional_data":false,"paper_date":"2016-05-20","paper":"/paper/fpnn-field-probing-neural-networks-for-3d","paper_url":"http://arxiv.org/abs/1605.06240v3","paper_title":"FPNN: Field Probing Neural Networks for 3D Data","code":"https://github.com/yangyanli/FPNN","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"Variational Shape Learner","metrics":{"Accuracy":"84.5%"},"uses_additional_data":false,"paper_date":"2017-05-17","paper":"/paper/learning-a-hierarchical-latent-variable-model","paper_url":"http://arxiv.org/abs/1705.05994v4","paper_title":"Learning a Hierarchical Latent-Variable Model of 3D Shapes","code":"https://github.com/lorenmt/vsl","n_code_links":1,"syntology":null}],"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":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3,"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"}}}