{"url":"/task/3d-object-classification","name":"3D Object Classification","slug":"3d-object-classification","description_markdown":"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)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":93,"papers_with_code":47,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":2,"parent_tasks":3},"benchmarks":[{"leaderboard":"/sota/3d-object-classification-on-modelnet40","slug":"3d-object-classification-on-modelnet40","dataset":"ModelNet40","dataset_url":"/dataset/modelnet","rows_in_archive":7,"metrics":["Classification Accuracy"],"first_row_in_archive_order":{"model":"Ours","paper_title":"Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation","paper_url":"/paper/exploiting-inductive-bias-in-transformer-for","paper_date":"2023-04-27","arxiv_id":"2304.14124","code_links":[{"title":"jiamang/ibt","url":"https://github.com/jiamang/ibt"}],"syntology":null}},{"leaderboard":"/sota/3d-object-classification-on-modelnet10","slug":"3d-object-classification-on-modelnet10","dataset":"ModelNet10","dataset_url":"/dataset/modelnet","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PolyNet","paper_title":"PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation","paper_url":"/paper/polynet-polynomial-neural-network-for-3d","paper_date":"2021-10-15","arxiv_id":"2110.07882","code_links":[{"title":"myavartanoo/PolyNet_PyTorch","url":"https://github.com/myavartanoo/PolyNet_PyTorch"}],"syntology":null}},{"leaderboard":"/sota/3d-object-classification-on-3r-scan-1","slug":"3d-object-classification-on-3r-scan-1","dataset":"3R-Scan","dataset_url":"/dataset/3r-scan","rows_in_archive":2,"metrics":["Top-10 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"SceneGraphFusion","paper_title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","paper_url":"/paper/scenegraphfusion-incremental-3d-scene-graph","paper_date":"2021-03-27","arxiv_id":"2103.14898","code_links":[{"title":"ShunChengWu/SceneGraphFusion","url":"https://github.com/ShunChengWu/SceneGraphFusion"},{"title":"ShunChengWu/3DSSG","url":"https://github.com/ShunChengWu/3DSSG"}],"syntology":null}},{"leaderboard":"/sota/3d-object-classification-on-remote-flash","slug":"3d-object-classification-on-remote-flash","dataset":"Remote Flash LiDAR Vehicles Dataset","dataset_url":"/dataset/remote-flash-lidar-vehicles-dataset","rows_in_archive":1,"metrics":["mean average precision"],"first_row_in_archive_order":{"model":"YOLO-X","paper_title":"Real-time object detection and tracking using flash LiDAR imagery","paper_url":"/paper/real-time-object-detection-and-tracking-using","paper_date":"2024-06-07","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/modelnet","name":"ModelNet","full_name":"","num_papers_in_archive":1406},{"url":"/dataset/3r-scan","name":"3RScan","full_name":"","num_papers_in_archive":44},{"url":"/dataset/cyclone-data","name":"Cyclone Data","full_name":"global cyclone data from 1841 to 2021","num_papers_in_archive":2},{"url":"/dataset/cy101-dataset","name":"CY101 Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/euen17037-daylight-and-view-standard","name":"EUEN17037_Daylight_and_View_Standard_TestDataSet","full_name":"","num_papers_in_archive":1},{"url":"/dataset/remote-flash-lidar-vehicles-dataset","name":"Remote Flash LiDAR Vehicles Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ur5-tool-dataset","name":"UR5 Tool Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/cube-engraving-classification","name":"Cube Engraving Classification"},{"url":"/task/generative-3d-object-classification","name":"Generative 3D Object Classification"}],"parent_tasks":[{"url":"/task/3d","name":"3D"},{"url":"/task/3d-classification","name":"3D Classification"},{"url":"/task/3d-point-cloud-classification","name":"3D Point Cloud Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":47,"tagged_in_all":93,"items":[{"url":"/paper/pointllm-empowering-large-language-models-to","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","date":"2023-08-31","arxiv_id":"2308.16911","repositories_listed":3,"syntology":null},{"url":"/paper/pointmixer-mlp-mixer-for-point-cloud","title":"PointMixer: MLP-Mixer for Point Cloud Understanding","date":"2021-11-22","arxiv_id":"2111.11187","repositories_listed":3,"syntology":null},{"url":"/paper/learning-geometry-disentangled-representation","title":"Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud","date":"2020-12-20","arxiv_id":"2012.10921","repositories_listed":3,"syntology":null},{"url":"/paper/spherical-kernel-for-efficient-graph","title":"Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds","date":"2019-09-20","arxiv_id":"1909.09287","repositories_listed":3,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/revisiting-point-cloud-classification-a-new","title":"Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data","date":"2019-08-13","arxiv_id":"1908.04616","repositories_listed":3,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/diff-op3d-bridging-2d-diffusion-for-open-pose","title":"Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges","date":"2023-12-12","arxiv_id":"2312.07039","repositories_listed":2,"syntology":null},{"url":"/paper/uni3d-exploring-unified-3d-representation-at","title":"Uni3D: Exploring Unified 3D Representation at Scale","date":"2023-10-10","arxiv_id":"2310.06773","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/scenegraphfusion-incremental-3d-scene-graph","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","date":"2021-03-27","arxiv_id":"2103.14898","repositories_listed":2,"syntology":null},{"url":"/paper/point-transformer","title":"Point Transformer","date":"2020-11-02","arxiv_id":"2011.00931","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/3d-point-capsule-networks","title":"3D Point Capsule Networks","date":"2018-12-27","arxiv_id":"1812.10775","repositories_listed":2,"syntology":null},{"url":"/paper/dynamic-edge-conditioned-filters-in","title":"Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs","date":"2017-04-10","arxiv_id":"1704.02901","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/pointnet-with-kan-versus-pointnet-with-mlp","title":"PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets","date":"2024-10-14","arxiv_id":"2410.10084","repositories_listed":1,"syntology":null},{"url":"/paper/pcp-mae-learning-to-predict-centers-for-point","title":"PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders","date":"2024-08-16","arxiv_id":"2408.08753","repositories_listed":1,"syntology":null},{"url":"/paper/dc3do-diffusion-classifier-for-3d-objects","title":"DC3DO: Diffusion Classifier for 3D Objects","date":"2024-08-13","arxiv_id":"2408.06693","repositories_listed":1,"syntology":null},{"url":"/paper/minigpt-3d-efficiently-aligning-3d-point","title":"MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors","date":"2024-05-02","arxiv_id":"2405.01413","repositories_listed":1,"syntology":null},{"url":"/paper/classifying-objects-in-3d-point-clouds-using","title":"Classifying Objects in 3D Point Clouds Using Recurrent Neural Network: A GRU LSTM Hybrid Approach","date":"2024-03-09","arxiv_id":"2403.05950","repositories_listed":1,"syntology":null},{"url":"/paper/point-cloud-self-supervised-learning-via-3d","title":"Point Cloud Self-supervised Learning via 3D to Multi-view Masked Autoencoder","date":"2023-11-17","arxiv_id":"2311.10887","repositories_listed":1,"syntology":null},{"url":"/paper/extending-multi-modal-contrastive","title":"Extending Multi-modal Contrastive Representations","date":"2023-10-13","arxiv_id":"2310.08884","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/crossmoco-multi-modal-momentum-contrastive","title":"CrossMoCo: Multi-modal Momentum Contrastive Learning for Point Cloud","date":"2023-06-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-inductive-bias-in-transformer-for","title":"Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation","date":"2023-04-27","arxiv_id":"2304.14124","repositories_listed":1,"syntology":null},{"url":"/paper/densely-connected-g-invariant-deep-neural","title":"Densely Connected $G$-invariant Deep Neural Networks with Signed Permutation Representations","date":"2023-03-08","arxiv_id":"2303.04614","repositories_listed":1,"syntology":null},{"url":"/paper/parot-patch-wise-rotation-invariant-network","title":"PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration","date":"2023-02-06","arxiv_id":"2302.02535","repositories_listed":1,"syntology":null},{"url":"/paper/improved-training-for-3d-point-cloud","title":"Improved Training for 3D Point Cloud Classification","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mate-masked-autoencoders-are-online-3d-test","title":"MATE: Masked Autoencoders are Online 3D Test-Time Learners","date":"2022-11-21","arxiv_id":"2211.11432","repositories_listed":1,"syntology":null},{"url":"/paper/data-augmentation-free-unsupervised-learning","title":"Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding","date":"2022-10-06","arxiv_id":"2210.02798","repositories_listed":1,"syntology":null},{"url":"/paper/crosspoint-self-supervised-cross-modal","title":"CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding","date":"2022-03-01","arxiv_id":"2203.00680","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/on-automatic-data-augmentation-for-3d-point","title":"On Automatic Data Augmentation for 3D Point Cloud Classification","date":"2021-12-11","arxiv_id":"2112.06029","repositories_listed":1,"syntology":null},{"url":"/paper/diffconv-analyzing-irregular-point-clouds","title":"diffConv: Analyzing Irregular Point Clouds with an Irregular View","date":"2021-11-29","arxiv_id":"2111.14658","repositories_listed":1,"syntology":null},{"url":"/paper/polynet-polynomial-neural-network-for-3d","title":"PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation","date":"2021-10-15","arxiv_id":"2110.07882","repositories_listed":1,"syntology":null},{"url":"/paper/regularization-strategy-for-point-cloud-via","title":"Regularization Strategy for Point Cloud via Rigidly Mixed Sample","date":"2021-02-03","arxiv_id":"2102.01929","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}