{"url":"/dataset/partnet","name":"PartNet","full_name":null,"description_markdown":"PartNet is a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. The dataset consists of 573,585 part instances over 26,671 3D models covering 24 object categories. This dataset enables and serves as a catalyst for many tasks such as shape analysis, dynamic 3D scene modeling and simulation, affordance analysis, and others.\r\n\r\nSource: [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](/paper/partnet-a-large-scale-benchmark-for-fine)\r\nImage Source: [https://cs.stanford.edu/~kaichun/partnet/](https://cs.stanford.edu/~kaichun/partnet/)","description_withheld":null,"homepage":"https://cs.stanford.edu/~kaichun/partnet/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/partnet-a-large-scale-benchmark-for-fine","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","first_author":"Kaichun Mo","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"3D","url":"/datasets/modality/3d"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Instance Segmentation","url":"/task/instance-segmentation","datasets_with_task":"/datasets/task/instance-segmentation"},{"name":"3D Semantic Segmentation","url":"/task/3d-semantic-segmentation","datasets_with_task":"/datasets/task/3d-semantic-segmentation"},{"name":"3D Instance Segmentation","url":"/task/3d-instance-segmentation-1","datasets_with_task":"/datasets/task/3d-instance-segmentation-1"}],"languages":[],"variants":["PartNet"],"data_loaders":[],"num_papers_in_archive":156,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-semantic-segmentation-on-partnet","task":"3D Semantic Segmentation","dataset_variant":"PartNet","rows":6,"metrics":["mIOU"],"first_row_in_archive_order":{"model":"CSN","paper":"/paper/cross-shape-graph-convolutional-networks","metrics":{"mIOU":"62.1"},"code_links":[{"title":"marios2019/CSN","url":"https://github.com/marios2019/CSN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-instance-segmentation-on-partnet","task":"3D Instance Segmentation","dataset_variant":"PartNet","rows":3,"metrics":["mAP50"],"first_row_in_archive_order":{"model":"Semantic Segmentation-Assisted Instance Feature Fusion","paper":"/paper/semantic-segmentation-assisted-instance","metrics":{"mAP50":"64.1"},"code_links":[{"title":"isunchy/3d_instance_segmentation","url":"https://github.com/isunchy/3d_instance_segmentation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/instance-segmentation-on-partnet","task":"Instance Segmentation","dataset_variant":"PartNet","rows":1,"metrics":["mAP50"],"first_row_in_archive_order":{"model":"PE","paper":"/paper/point-cloud-instance-segmentation-using","metrics":{"mAP50":"57.5"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/semantic-segmentation-assisted-instance","title":"Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation","date":"2022-08-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fg-net-fast-large-scale-lidar-point","title":"FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling","date":"2020-12-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-3d-learning-for-shape-analysis","title":"Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination","date":"2020-08-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":0,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-closer-look-at-local-aggregation-operators","title":"A Closer Look at Local Aggregation Operators in Point Cloud Analysis","date":"2020-07-02","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":0,"samples_unverified":9,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cross-shape-graph-convolutional-networks","title":"Cross-Shape Attention for Part Segmentation of 3D Point Clouds","date":"2020-03-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/point-cloud-instance-segmentation-using","title":"Point Cloud Instance Segmentation using Probabilistic Embeddings","date":"2019-11-30","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/deepgcns-making-gcns-go-as-deep-as-cnns","title":"DeepGCNs: Making GCNs Go as Deep as CNNs","date":"2019-10-15","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":1,"samples_unverified":8,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/partnet-a-large-scale-benchmark-for-fine","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","date":"2018-12-06","rows_on_this_dataset":2,"code_links":5,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":4,"samples_harvested":30,"samples_ran":3,"samples_unverified":27,"pointer_only_for_licence":10,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}