{"url":"/sota/3d-point-cloud-linear-classification-on","task":{"name":"3D Point Cloud Linear Classification","url":"/task/3d-point-cloud-linear-classification","note":null},"dataset":{"name":"ModelNet40","url":"/dataset/modelnet"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Training a linear classifier(e.g. SVM) on the embeddings/representations of 3D point clouds. The embeddings/representations are usually trained in an unsupervised manner.","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":["Overall Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Overall Accuracy":"higher"}},"counts":{"rows":20,"rows_with_code":16,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":7},"rows":[{"rank_in_archive_order":1,"model":"Point-JEPA","metrics":{"Overall Accuracy":"93.7±0.2"},"uses_additional_data":true,"paper_date":"2024-04-25","paper":"/paper/point-jepa-a-joint-embedding-predictive","paper_url":"https://arxiv.org/abs/2404.16432v5","paper_title":"Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud","code":"https://github.com/Ayumu-J-S/Point-JEPA","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"ReCon++","metrics":{"Overall Accuracy":"93.6"},"uses_additional_data":false,"paper_date":"2024-02-27","paper":"/paper/shapellm-universal-3d-object-understanding","paper_url":"https://arxiv.org/abs/2402.17766v3","paper_title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","code":"https://github.com/qizekun/ShapeLLM","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":8,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"I2P-MAE","metrics":{"Overall Accuracy":"93.4"},"uses_additional_data":true,"paper_date":"2022-12-13","paper":"/paper/learning-3d-representations-from-2d-pre","paper_url":"https://arxiv.org/abs/2212.06785v1","paper_title":"Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders","code":"https://github.com/zrrskywalker/i2p-mae","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"ReCon","metrics":{"Overall Accuracy":"93.4"},"uses_additional_data":true,"paper_date":"2023-02-05","paper":"/paper/contrast-with-reconstruct-contrastive-3d","paper_url":"https://arxiv.org/abs/2302.02318v2","paper_title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","code":"https://github.com/qizekun/ReCon","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"Point-M2AE","metrics":{"Overall Accuracy":"92.9"},"uses_additional_data":true,"paper_date":"2022-05-28","paper":"/paper/point-m2ae-multi-scale-masked-autoencoders","paper_url":"https://arxiv.org/abs/2205.14401v2","paper_title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","code":"https://github.com/zrrskywalker/i2p-mae","n_code_links":3,"syntology":null},{"rank_in_archive_order":6,"model":"IAE (DGCNN)","metrics":{"Overall Accuracy":"92.1"},"uses_additional_data":true,"paper_date":"2022-01-03","paper":"/paper/implicit-autoencoder-for-point-cloud-self","paper_url":"https://arxiv.org/abs/2201.00785v5","paper_title":"Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning","code":"https://github.com/simingyan/iae","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"AdaCrossNet","metrics":{"Overall Accuracy":"91.8"},"uses_additional_data":true,"paper_date":"2025-01-02","paper":"/paper/adacrossnet-adaptive-dynamic-loss-weighting","paper_url":"https://inass.org/wp-content/uploads/2024/10/2025022911-2.pdf","paper_title":"AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud Learning","code":"https://github.com/virgantara/AdaCrossNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"CrossMoCo","metrics":{"Overall 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":9,"model":"CrossPoint","metrics":{"Overall Accuracy":"91.2"},"uses_additional_data":true,"paper_date":"2022-03-01","paper":"/paper/crosspoint-self-supervised-cross-modal","paper_url":"https://arxiv.org/abs/2203.00680v3","paper_title":"CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding","code":"https://github.com/mohamedafham/crosspoint","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":10,"model":"STRL","metrics":{"Overall Accuracy":"90.9"},"uses_additional_data":false,"paper_date":"2021-09-01","paper":"/paper/spatio-temporal-self-supervised","paper_url":"https://arxiv.org/abs/2109.00179v1","paper_title":"Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds","code":"https://github.com/yichen928/STRL","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":11,"model":"PSG-Net","metrics":{"Overall Accuracy":"90.9"},"uses_additional_data":false,"paper_date":"2021-12-09","paper":"/paper/progressive-seed-generation-auto-encoder-for-1","paper_url":"https://arxiv.org/abs/2112.05213v1","paper_title":"Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"PointOE","metrics":{"Overall Accuracy":"90.7"},"uses_additional_data":false,"paper_date":"2020-08-01","paper":"/paper/self-supervised-learning-of-point-clouds-via","paper_url":"https://arxiv.org/abs/2008.00305v2","paper_title":"Self-supervised Learning of Point Clouds via Orientation Estimation","code":"https://github.com/OmidPoursaeed/Self_supervised_Learning_Point_Clouds","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Point-Jigsaw","metrics":{"Overall Accuracy":"90.6"},"uses_additional_data":false,"paper_date":"2019-01-24","paper":"/paper/context-prediction-for-unsupervised-deep","paper_url":"https://arxiv.org/abs/1901.08396v2","paper_title":"Self-Supervised Deep Learning on Point Clouds by Reconstructing Space","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"MID-FC","metrics":{"Overall Accuracy":"90.3"},"uses_additional_data":false,"paper_date":"2020-08-03","paper":"/paper/unsupervised-3d-learning-for-shape-analysis","paper_url":"https://arxiv.org/abs/2008.01068v2","paper_title":"Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination","code":"https://github.com/Microsoft/O-CNN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"VIP-GAN","metrics":{"Overall Accuracy":"90.2"},"uses_additional_data":false,"paper_date":"2018-11-07","paper":"/paper/view-inter-prediction-gan-unsupervised","paper_url":"http://arxiv.org/abs/1811.02744v1","paper_title":"View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"OcCo","metrics":{"Overall Accuracy":"89.2"},"uses_additional_data":false,"paper_date":"2020-10-02","paper":"/paper/pre-training-by-completing-point-clouds","paper_url":"https://arxiv.org/abs/2010.01089v3","paper_title":"Unsupervised Point Cloud Pre-Training via Occlusion Completion","code":"https://github.com/hansen7/OcCo","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"FoldingNet","metrics":{"Overall Accuracy":"88.4"},"uses_additional_data":false,"paper_date":"2017-12-19","paper":"/paper/foldingnet-point-cloud-auto-encoder-via-deep","paper_url":"http://arxiv.org/abs/1712.07262v2","paper_title":"FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation","code":"https://github.com/AnTao97/UnsupervisedPointCloudReconstruction","n_code_links":3,"syntology":null},{"rank_in_archive_order":18,"model":"MAE-VAE","metrics":{"Overall Accuracy":"88.4"},"uses_additional_data":false,"paper_date":"2019-07-30","paper":"/paper/multi-angle-point-cloud-vae-unsupervised","paper_url":"https://arxiv.org/abs/1907.12704v1","paper_title":"Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"SO-Net","metrics":{"Overall Accuracy":"87.5"},"uses_additional_data":false,"paper_date":"2018-03-12","paper":"/paper/so-net-self-organizing-network-for-point","paper_url":"http://arxiv.org/abs/1803.04249v4","paper_title":"SO-Net: Self-Organizing Network for Point Cloud Analysis","code":"https://github.com/lijx10/SO-Net","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"3D-GAN","metrics":{"Overall Accuracy":"83.3"},"uses_additional_data":false,"paper_date":"2016-10-24","paper":"/paper/learning-a-probabilistic-latent-space-of","paper_url":"http://arxiv.org/abs/1610.07584v2","paper_title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","code":"https://github.com/zck119/3dgan-release","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}}],"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":8,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":8,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":22,"n_unverified":30,"n_samples":52,"n_pointer_only_licence":5,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":22,"n_unverified":30,"n_samples":52,"n_pointer_only_licence":5,"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"}}}