{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/partnet-a-large-scale-benchmark-for-fine","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","arxiv_id":"1812.02713","date":"2018-12-06","proceeding":"CVPR 2019 6","authors":["Kaichun Mo","Shilin Zhu","Angel X. Chang","Li Yi","Subarna Tripathi","Leonidas J. Guibas","Hao Su"],"abstract":"We present PartNet: a consistent, large-scale dataset of 3D objects annotated\nwith fine-grained, instance-level, and hierarchical 3D part information. Our\ndataset consists of 573,585 part instances over 26,671 3D models covering 24\nobject categories. This dataset enables and serves as a catalyst for many tasks\nsuch as shape analysis, dynamic 3D scene modeling and simulation, affordance\nanalysis, and others. Using our dataset, we establish three benchmarking tasks\nfor evaluating 3D part recognition: fine-grained semantic segmentation,\nhierarchical semantic segmentation, and instance segmentation. We benchmark\nfour state-of-the-art 3D deep learning algorithms for fine-grained semantic\nsegmentation and three baseline methods for hierarchical semantic segmentation.\nWe also propose a novel method for part instance segmentation and demonstrate\nits superior performance over existing methods.","url_abs":"http://arxiv.org/abs/1812.02713v1","url_pdf":"http://arxiv.org/pdf/1812.02713v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"partnet-a-large-scale-benchmark-for-fine","repo_url":"https://github.com/LebronGG/PointCnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"partnet-a-large-scale-benchmark-for-fine","repo_url":"https://github.com/c3210927/point_cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"partnet-a-large-scale-benchmark-for-fine","repo_url":"https://github.com/daerduoCarey/partnet_anno_system","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"partnet-a-large-scale-benchmark-for-fine","repo_url":"https://github.com/daerduoCarey/partnet_dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"partnet-a-large-scale-benchmark-for-fine","repo_url":"https://github.com/yangyanli/PointCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-instance-segmentation-1","task_name":"3D Instance Segmentation"},{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"partnet","name":"PartNet","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-instance-segmentation-on-partnet","task":"3D Instance Segmentation","dataset":"PartNet","model":"Partnet","rank_in_archive_order":3,"of":3,"metrics":{"mAP50":" 54.4"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-partnet","task":"3D Semantic Segmentation","dataset":"PartNet","model":"PartNet","rank_in_archive_order":6,"of":6,"metrics":{"mIOU":"43.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1812.02713","atlas_url":"https://app.syntology.ai/?focus=1812.02713","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}