{"url":"/task/3d-open-vocabulary-instance-segmentation","name":"3D Open-Vocabulary Instance Segmentation","slug":"3d-open-vocabulary-instance-segmentation","description_markdown":"Open-vocabulary 3D instance segmentation is a computer vision task that involves identifying and delineating individual objects or instances within a three-dimensional (3D) scene without prior knowledge of a fixed set of object classes or categories. In other words, it extends traditional instance segmentation to a scenario where the number and types of objects present in the 3D environment are not predefined or limited to a specific vocabulary.","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":14,"papers_with_code":9,"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":4,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/3d-open-vocabulary-instance-segmentation-on-1","slug":"3d-open-vocabulary-instance-segmentation-on-1","dataset":"Replica","dataset_url":"/dataset/replica","rows_in_archive":7,"metrics":["mAP"],"first_row_in_archive_order":{"model":"Open-YOLO 3D","paper_title":"Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation","paper_url":"/paper/open-yolo-3d-towards-fast-and-accurate-open","paper_date":"2024-06-04","arxiv_id":"2406.02548","code_links":[{"title":"aminebdj/openyolo3d","url":"https://github.com/aminebdj/openyolo3d"}],"syntology":{"n":11,"n_ran":4,"n_unverified":7,"n_pointer_only":11}}},{"leaderboard":"/sota/3d-open-vocabulary-instance-segmentation-on","slug":"3d-open-vocabulary-instance-segmentation-on","dataset":"ScanNet200","dataset_url":"/dataset/scannet200","rows_in_archive":6,"metrics":["mAP","AP50","AP25","AP Head","AP Common","AP Tail"],"first_row_in_archive_order":{"model":"Any3DIS","paper_title":"Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking","paper_url":"/paper/any3dis-class-agnostic-3d-instance","paper_date":"2024-11-25","arxiv_id":"2411.16183","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-open-vocabulary-instance-segmentation-on-2","slug":"3d-open-vocabulary-instance-segmentation-on-2","dataset":"S3DIS","dataset_url":"/dataset/s3dis","rows_in_archive":4,"metrics":["AP50 Base B8/N4 ","AP50 Novel B8/N4","AP50 Base B6/N6","AP50 Novel B6/N6"],"first_row_in_archive_order":{"model":"Open3DIS","paper_title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","paper_url":"/paper/open3dis-open-vocabulary-3d-instance","paper_date":"2023-12-17","arxiv_id":"2312.10671","code_links":[{"title":"VinAIResearch/Open3DIS","url":"https://github.com/VinAIResearch/Open3DIS"}],"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-open-vocabulary-instance-segmentation-on-3","slug":"3d-open-vocabulary-instance-segmentation-on-3","dataset":"STPLS3D","dataset_url":"/dataset/stpls3d","rows_in_archive":3,"metrics":["AP50"],"first_row_in_archive_order":{"model":"OPENINS3D","paper_title":"OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation","paper_url":"/paper/openins3d-snap-and-lookup-for-3d-open","paper_date":"2023-09-01","arxiv_id":"2309.00616","code_links":[{"title":"Pointcept/OpenIns3D","url":"https://github.com/Pointcept/OpenIns3D"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/s3dis","name":"S3DIS","full_name":"Stanford 3D Indoor Scene Dataset (S3DIS)","num_papers_in_archive":488},{"url":"/dataset/replica","name":"Replica","full_name":"","num_papers_in_archive":414},{"url":"/dataset/scannet200","name":"ScanNet200","full_name":"","num_papers_in_archive":45},{"url":"/dataset/stpls3d","name":"STPLS3D","full_name":"","num_papers_in_archive":36}],"subtasks":[],"parent_tasks":[],"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":9,"of":9,"tagged_in_all":14,"items":[{"url":"/paper/pointclip-v2-adapting-clip-for-powerful-3d","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","date":"2022-11-21","arxiv_id":"2211.11682","repositories_listed":2,"syntology":{"n":12,"n_ran":5,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/pointclip-point-cloud-understanding-by-clip","title":"PointCLIP: Point Cloud Understanding by CLIP","date":"2021-12-04","arxiv_id":"2112.02413","repositories_listed":2,"syntology":null},{"url":"/paper/open-yolo-3d-towards-fast-and-accurate-open","title":"Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation","date":"2024-06-04","arxiv_id":"2406.02548","repositories_listed":1,"syntology":{"n":11,"n_ran":4,"n_unverified":7,"n_pointer_only":11}},{"url":"/paper/open3dis-open-vocabulary-3d-instance","title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","date":"2023-12-17","arxiv_id":"2312.10671","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/ovir-3d-open-vocabulary-3d-instance-retrieval","title":"OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data","date":"2023-11-06","arxiv_id":"2311.02873","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/openins3d-snap-and-lookup-for-3d-open","title":"OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation","date":"2023-09-01","arxiv_id":"2309.00616","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/openmask3d-open-vocabulary-3d-instance","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","date":"2023-06-23","arxiv_id":"2306.13631","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/language-driven-open-vocabulary-3d-scene","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","date":"2022-11-29","arxiv_id":"2211.16312","repositories_listed":1,"syntology":null},{"url":"/paper/openscene-3d-scene-understanding-with-open","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","date":"2022-11-28","arxiv_id":"2211.15654","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}],"syntology_records":7,"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"}}