{"url":"/task/3d-object-recognition","name":"3D Object Recognition","slug":"3d-object-recognition","description_markdown":"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>","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":97,"papers_with_code":32,"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":8,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/3d-object-recognition-on-modelnet40","slug":"3d-object-recognition-on-modelnet40","dataset":"ModelNet40","dataset_url":"/dataset/modelnet","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"R2-MLP-36","paper_title":"R2-MLP: Round-Roll MLP for Multi-View 3D Object Recognition","paper_url":"/paper/r2-mlp-round-roll-mlp-for-multi-view-3d","paper_date":"2022-11-20","arxiv_id":"2211.11085","code_links":[{"title":"shanshuo/MVT","url":"https://github.com/shanshuo/MVT"},{"title":"shanshuo/R2-MLP","url":"https://github.com/shanshuo/R2-MLP"}],"syntology":null}},{"leaderboard":"/sota/3d-object-recognition-on-cube-engraving","slug":"3d-object-recognition-on-cube-engraving","dataset":"Cube Engraving","dataset_url":"/dataset/cube","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MeshWalker (ours)","paper_title":"MeshWalker: Deep Mesh Understanding by Random Walks","paper_url":"/paper/meshwalker-deep-mesh-understanding-by-random","paper_date":"2020-06-09","arxiv_id":"2006.05353","code_links":[{"title":"AlonLahav/MeshWalker","url":"https://github.com/AlonLahav/MeshWalker"}],"syntology":null}},{"leaderboard":"/sota/3d-object-recognition-on-shrec11-split10-10","slug":"3d-object-recognition-on-shrec11-split10-10","dataset":"SHREC11, Split10-10","dataset_url":null,"rows_in_archive":1,"metrics":["Per-Class Accuracy"],"first_row_in_archive_order":{"model":"MeshWalker (ours)","paper_title":"MeshWalker: Deep Mesh Understanding by Random Walks","paper_url":"/paper/meshwalker-deep-mesh-understanding-by-random","paper_date":"2020-06-09","arxiv_id":"2006.05353","code_links":[{"title":"AlonLahav/MeshWalker","url":"https://github.com/AlonLahav/MeshWalker"}],"syntology":null}},{"leaderboard":"/sota/3d-object-recognition-on-shrec11-split16-4","slug":"3d-object-recognition-on-shrec11-split16-4","dataset":"SHREC11, Split16-4","dataset_url":"/dataset/shrec","rows_in_archive":1,"metrics":["Per-Class Accuracy"],"first_row_in_archive_order":{"model":"MeshWalker (ours)","paper_title":"MeshWalker: Deep Mesh Understanding by Random Walks","paper_url":"/paper/meshwalker-deep-mesh-understanding-by-random","paper_date":"2020-06-09","arxiv_id":"2006.05353","code_links":[{"title":"AlonLahav/MeshWalker","url":"https://github.com/AlonLahav/MeshWalker"}],"syntology":null}}],"datasets":[{"url":"/dataset/modelnet","name":"ModelNet","full_name":"","num_papers_in_archive":1406},{"url":"/dataset/shrec","name":"SHREC","full_name":"SHape REtrieval Contest","num_papers_in_archive":32},{"url":"/dataset/washington-rgb-d","name":"Washington RGB-D","full_name":"Washington RGB-D","num_papers_in_archive":15},{"url":"/dataset/cube","name":"Cube++","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/doors","name":"DOORS","full_name":"Dataset fOr bOuldeRs Segmentation","num_papers_in_archive":3},{"url":"/dataset/cy101-dataset","name":"CY101 Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/the-rbo-dataset-of-articulated-objects-and","name":"The RBO Dataset of Articulated Objects and Interactions","full_name":"","num_papers_in_archive":1},{"url":"/dataset/corn-seeds-dataset","name":"Corn Seeds Dataset","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/object-recognition","name":"Object Recognition"}],"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":32,"tagged_in_all":97,"items":[{"url":"/paper/blenderproc","title":"BlenderProc","date":"2019-10-25","arxiv_id":"1911.01911","repositories_listed":4,"syntology":null},{"url":"/paper/learning-a-probabilistic-latent-space-of","title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","date":"2016-10-24","arxiv_id":"1610.07584","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/r2-mlp-round-roll-mlp-for-multi-view-3d","title":"R2-MLP: Round-Roll MLP for Multi-View 3D Object Recognition","date":"2022-11-20","arxiv_id":"2211.11085","repositories_listed":2,"syntology":null},{"url":"/paper/mvt-multi-view-vision-transformer-for-3d","title":"MVT: Multi-view Vision Transformer for 3D Object Recognition","date":"2021-10-25","arxiv_id":"2110.13083","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/scenegraphnet-neural-message-passing-for-3d","title":"SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation","date":"2019-07-25","arxiv_id":"1907.11308","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/fpnn-field-probing-neural-networks-for-3d","title":"FPNN: Field Probing Neural Networks for 3D Data","date":"2016-05-20","arxiv_id":"1605.06240","repositories_listed":2,"syntology":null},{"url":"/paper/volumetric-and-multi-view-cnns-for-object","title":"Volumetric and Multi-View CNNs for Object Classification on 3D Data","date":"2016-04-12","arxiv_id":"1604.03265","repositories_listed":2,"syntology":null},{"url":"/paper/sparse-3d-convolutional-neural-networks","title":"Sparse 3D convolutional neural networks","date":"2015-05-12","arxiv_id":"1505.02890","repositories_listed":2,"syntology":null},{"url":"/paper/sasep-saliency-aware-structured-separation-of-1","title":"SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds","date":"2025-06-16","arxiv_id":"2506.13224","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/topology-guided-knowledge-distillation-for","title":"Topology-Guided Knowledge Distillation for Efficient Point Cloud Processing","date":"2025-05-12","arxiv_id":"2505.08101","repositories_listed":1,"syntology":null},{"url":"/paper/targeted-view-invariant-adversarial","title":"Targeted View-Invariant Adversarial Perturbations for 3D Object Recognition","date":"2024-12-17","arxiv_id":"2412.13376","repositories_listed":1,"syntology":null},{"url":"/paper/improving-3d-semi-supervised-learning-by","title":"Improving 3D Semi-supervised Learning by Effectively Utilizing All Unlabelled Data","date":"2024-09-21","arxiv_id":"2409.13977","repositories_listed":1,"syntology":null},{"url":"/paper/one-noise-to-rule-them-all-multi-view","title":"One Noise to Rule Them All: Multi-View Adversarial Attacks with Universal Perturbation","date":"2024-04-02","arxiv_id":"2404.02287","repositories_listed":1,"syntology":null},{"url":"/paper/lifting-multi-view-detection-and-tracking-to","title":"Lifting Multi-View Detection and Tracking to the Bird's Eye View","date":"2024-03-19","arxiv_id":"2403.12573","repositories_listed":1,"syntology":null},{"url":"/paper/fsd-fast-self-supervised-single-rgb-d-to","title":"FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects","date":"2023-10-19","arxiv_id":"2310.12974","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-object-categorization-for","title":"Enhancing Fine-Grained 3D Object Recognition using Hybrid Multi-Modal Vision Transformer-CNN Models","date":"2022-10-03","arxiv_id":"2210.04613","repositories_listed":1,"syntology":null},{"url":"/paper/omni3d-a-large-benchmark-and-model-for-3d","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","date":"2022-07-21","arxiv_id":"2207.10660","repositories_listed":1,"syntology":null},{"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/explainability-aware-one-point-attack-for","title":"Explainability-Aware One Point Attack for Point Cloud Neural Networks","date":"2021-10-08","arxiv_id":"2110.04158","repositories_listed":1,"syntology":null},{"url":"/paper/lifelong-3d-object-recognition-and-grasp","title":"Lifelong 3D Object Recognition and Grasp Synthesis Using Dual Memory Recurrent Self-Organization Networks","date":"2021-09-23","arxiv_id":"2109.11544","repositories_listed":1,"syntology":null},{"url":"/paper/3d-den-open-ended-3d-object-recognition-using","title":"3D_DEN: Open-ended 3D Object Recognition using Dynamically Expandable Networks","date":"2020-09-15","arxiv_id":"2009.07213","repositories_listed":1,"syntology":null},{"url":"/paper/meshwalker-deep-mesh-understanding-by-random","title":"MeshWalker: Deep Mesh Understanding by Random Walks","date":"2020-06-09","arxiv_id":"2006.05353","repositories_listed":1,"syntology":null},{"url":"/paper/triangle-net-towards-robustness-in-point","title":"Triangle-Net: Towards Robustness in Point Cloud Learning","date":"2020-02-27","arxiv_id":"2003.00856","repositories_listed":1,"syntology":null},{"url":"/paper/task-aware-monocular-depth-estimation-for-3d","title":"Task-Aware Monocular Depth Estimation for 3D Object Detection","date":"2019-09-17","arxiv_id":"1909.07701","repositories_listed":1,"syntology":null},{"url":"/paper/dominant-set-clustering-and-pooling-for-multi","title":"Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition","date":"2019-06-04","arxiv_id":"1906.01592","repositories_listed":1,"syntology":null},{"url":"/paper/3d-object-recognition-with-ensemble-learning","title":"3D Object Recognition with Ensemble Learning --- A Study of Point Cloud-Based Deep Learning Models","date":"2019-04-17","arxiv_id":"1904.08159","repositories_listed":1,"syntology":null},{"url":"/paper/orthographicnet-a-deep-learning-approach-for","title":"OrthographicNet: A Deep Transfer Learning Approach for 3D Object Recognition in Open-Ended Domains","date":"2019-02-08","arxiv_id":"1902.03057","repositories_listed":1,"syntology":null},{"url":"/paper/pvnet-a-joint-convolutional-network-of-point","title":"PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognition","date":"2018-08-23","arxiv_id":"1808.07659","repositories_listed":1,"syntology":null},{"url":"/paper/multi-resolution-3d-convolutional-neural","title":"Multi-level 3D CNN for Learning Multi-scale Spatial Features","date":"2018-05-30","arxiv_id":"1805.12254","repositories_listed":1,"syntology":null},{"url":"/paper/triplet-center-loss-for-multi-view-3d-object","title":"Triplet-Center Loss for Multi-View 3D Object Retrieval","date":"2018-03-16","arxiv_id":"1803.06189","repositories_listed":1,"syntology":null}],"syntology_records":4,"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":1,"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"}}