{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/scannet200","name":"ScanNet200","full_name":null,"description_markdown":"The ScanNet200 benchmark studies 200-class 3D semantic segmentation - an order of magnitude more class categories than previous 3D scene understanding benchmarks. The source of scene data is identical to ScanNet, but parses a larger vocabulary for semantic and instance segmentation","description_withheld":null,"homepage":"http://kaldir.vc.in.tum.de/scannet_benchmark/","introduced_date":"2022-03-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/language-grounded-indoor-3d-semantic","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","first_author":"David Rozenberszki","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"3D","url":"/datasets/modality/3d"},{"name":"3d meshes","url":"/datasets/modality/3d-meshes"},{"name":"RGB-D","url":"/datasets/modality/rgb-d"}],"tasks":[{"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"},{"name":"3D Open-Vocabulary Instance Segmentation","url":"/task/3d-open-vocabulary-instance-segmentation","datasets_with_task":"/datasets/task/3d-open-vocabulary-instance-segmentation"}],"languages":[],"variants":["ScanNet200"],"data_loaders":[{"repo":"https://github.com/Pointcept/Pointcept","url":"https://github.com/Pointcept/Pointcept","frameworks":[]}],"num_papers_in_archive":45,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-semantic-segmentation-on-scannet200","task":"3D Semantic Segmentation","dataset_variant":"ScanNet200","rows":16,"metrics":["val mIoU","test mIoU"],"first_row_in_archive_order":{"model":"DITR","paper":"/paper/dino-in-the-room-leveraging-2d-foundation","metrics":{"test mIoU":"44.9","val mIoU":"41.2"},"code_links":[{"title":"VisualComputingInstitute/DITR","url":"https://github.com/VisualComputingInstitute/DITR"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-open-vocabulary-instance-segmentation-on","task":"3D Open-Vocabulary Instance Segmentation","dataset_variant":"ScanNet200","rows":6,"metrics":["mAP","AP50","AP25","AP Head","AP Common","AP Tail"],"first_row_in_archive_order":{"model":"Any3DIS","paper":"/paper/any3dis-class-agnostic-3d-instance","metrics":{"AP Common":"23.8","AP Head":"27.4","AP Tail":"26.4","mAP":"25.8"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-instance-segmentation-on-scannet200","task":"3D Instance Segmentation","dataset_variant":"ScanNet200","rows":5,"metrics":["mAP","mAP@25","mAP@50"],"first_row_in_archive_order":{"model":"ODIN","paper":"/paper/odin-a-single-model-for-2d-and-3d-perception","metrics":{"mAP":"31.5","mAP@25":"53.1","mAP@50":"45.3"},"code_links":[{"title":"ayushjain1144/odin","url":"https://github.com/ayushjain1144/odin"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":24,"of":24,"counts":{"papers_with_a_benchmark_row":24,"with_a_code_link":21,"where_syntology_ran_a_sample":13,"not_listed_spam_title":0,"listed":24,"listed_where_code_ran":13,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/dino-in-the-room-leveraging-2d-foundation","slug":"dino-in-the-room-leveraging-2d-foundation","title":"DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation","date":"2025-03-24","arxiv_id":"2503.18944","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sonata-self-supervised-learning-of-reliable","slug":"sonata-self-supervised-learning-of-reliable","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","date":"2025-03-20","arxiv_id":"2503.16429","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":3,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["Pointcept/Pointcept","facebookresearch/sonata"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sonata-self-supervised-learning-of-reliable#ran","syntology_url":"https://syntology.ai/paper/2503.16429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16429"}}}},{"paper":"/paper/bfanet-revisiting-3d-semantic-segmentation","slug":"bfanet-revisiting-3d-semantic-segmentation","title":"BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis","date":"2025-03-16","arxiv_id":"2503.12539","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/any3dis-class-agnostic-3d-instance","slug":"any3dis-class-agnostic-3d-instance","title":"Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking","date":"2024-11-25","arxiv_id":"2411.16183","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/msta3d-multi-scale-twin-attention-for-3d-1","slug":"msta3d-multi-scale-twin-attention-for-3d-1","title":"MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation","date":"2024-11-04","arxiv_id":"2411.01781","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/arkit-labelmaker-a-new-scale-for-indoor-3d","slug":"arkit-labelmaker-a-new-scale-for-indoor-3d","title":"ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding","date":"2024-10-17","arxiv_id":"2410.13924","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["cvg/labelmaker"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/arkit-labelmaker-a-new-scale-for-indoor-3d#ran","syntology_url":"https://syntology.ai/paper/2410.13924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13924"}}}},{"paper":"/paper/mamba24-8d-enhancing-global-interaction-in","slug":"mamba24-8d-enhancing-global-interaction-in","title":"Pamba: Enhancing Global Interaction in Point Clouds via State Space Model","date":"2024-06-25","arxiv_id":"2406.17442","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/open-yolo-3d-towards-fast-and-accurate-open","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":7,"pointer_only_for_licence":11,"official":{"repos":["aminebdj/openyolo3d"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/open-yolo-3d-towards-fast-and-accurate-open#ran","syntology_url":"https://syntology.ai/paper/2406.02548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02548"}}}},{"paper":"/paper/lsk3dnet-towards-effective-and-efficient-3d","slug":"lsk3dnet-towards-effective-and-efficient-3d","title":"LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels","date":"2024-03-22","arxiv_id":"2403.15173","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/oa-cnns-omni-adaptive-sparse-cnns-for-3d","slug":"oa-cnns-omni-adaptive-sparse-cnns-for-3d","title":"OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation","date":"2024-03-21","arxiv_id":"2403.14418","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/odin-a-single-model-for-2d-and-3d-perception","slug":"odin-a-single-model-for-2d-and-3d-perception","title":"ODIN: A Single Model for 2D and 3D Segmentation","date":"2024-01-04","arxiv_id":"2401.02416","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":6,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ayushjain1144/odin"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/odin-a-single-model-for-2d-and-3d-perception#ran","syntology_url":"https://syntology.ai/paper/2401.02416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02416"}}}},{"paper":"/paper/open3dis-open-vocabulary-3d-instance","slug":"open3dis-open-vocabulary-3d-instance","title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","date":"2023-12-17","arxiv_id":"2312.10671","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["VinAIResearch/Open3DIS"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/open3dis-open-vocabulary-3d-instance#ran","syntology_url":"https://syntology.ai/paper/2312.10671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10671"}}}},{"paper":"/paper/point-transformer-v3-simpler-faster-stronger","slug":"point-transformer-v3-simpler-faster-stronger","title":"Point Transformer V3: Simpler, Faster, Stronger","date":"2023-12-15","arxiv_id":"2312.10035","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["Pointcept/Pointcept","pointcept/pointtransformerv3"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/point-transformer-v3-simpler-faster-stronger#ran","syntology_url":"https://syntology.ai/paper/2312.10035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10035"}}}},{"paper":"/paper/oneformer3d-one-transformer-for-unified-point","slug":"oneformer3d-one-transformer-for-unified-point","title":"OneFormer3D: One Transformer for Unified Point Cloud Segmentation","date":"2023-11-24","arxiv_id":"2311.14405","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ponderv2-pave-the-way-for-3d-foundataion","slug":"ponderv2-pave-the-way-for-3d-foundataion","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","date":"2023-10-12","arxiv_id":"2310.08586","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/openins3d-snap-and-lookup-for-3d-open","slug":"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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["Pointcept/OpenIns3D"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/openins3d-snap-and-lookup-for-3d-open#ran","syntology_url":"https://syntology.ai/paper/2309.00616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00616"}}}},{"paper":"/paper/towards-large-scale-3d-representation","slug":"towards-large-scale-3d-representation","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","date":"2023-08-18","arxiv_id":"2308.09718","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/openmask3d-open-vocabulary-3d-instance","slug":"openmask3d-open-vocabulary-3d-instance","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","date":"2023-06-23","arxiv_id":"2306.13631","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["OpenMask3D/openmask3d"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/openmask3d-open-vocabulary-3d-instance#ran","syntology_url":"https://syntology.ai/paper/2306.13631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.13631"}}}},{"paper":"/paper/octformer-octree-based-transformers-for-3d","slug":"octformer-octree-based-transformers-for-3d","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","date":"2023-05-04","arxiv_id":"2305.03045","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":3,"official":{"repos":["octree-nn/octformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/octformer-octree-based-transformers-for-3d#ran","syntology_url":"https://syntology.ai/paper/2305.03045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.03045"}}}},{"paper":"/paper/isbnet-a-3d-point-cloud-instance-segmentation","slug":"isbnet-a-3d-point-cloud-instance-segmentation","title":"ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution","date":"2023-03-01","arxiv_id":"2303.00246","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["VinAIResearch/ISBNet"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/isbnet-a-3d-point-cloud-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2303.00246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.00246"}}}},{"paper":"/paper/mask3d-for-3d-semantic-instance-segmentation","slug":"mask3d-for-3d-semantic-instance-segmentation","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","date":"2022-10-06","arxiv_id":"2210.03105","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":7,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["jonasschult/mask3d"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mask3d-for-3d-semantic-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2210.03105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03105"}}}},{"paper":"/paper/language-grounded-indoor-3d-semantic","slug":"language-grounded-indoor-3d-semantic","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","date":"2022-04-16","arxiv_id":"2204.07761","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["RozDavid/LanguageGroundedSemseg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-grounded-indoor-3d-semantic#ran","syntology_url":"https://syntology.ai/paper/2204.07761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.07761"}}}},{"paper":"/paper/exploring-data-efficient-3d-scene","slug":"exploring-data-efficient-3d-scene","title":"Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts","date":"2020-12-16","arxiv_id":"2012.09165","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/4d-spatio-temporal-convnets-minkowski","slug":"4d-spatio-temporal-convnets-minkowski","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","date":"2019-04-18","arxiv_id":"1904.08755","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["StanfordVL/MinkowskiEngine"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/4d-spatio-temporal-convnets-minkowski#ran","syntology_url":"https://syntology.ai/paper/1904.08755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08755"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/dino-in-the-room-leveraging-2d-foundation","slug":"dino-in-the-room-leveraging-2d-foundation","title":"DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation","date":"2025-03-24","arxiv_id":"2503.18944","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sonata-self-supervised-learning-of-reliable","slug":"sonata-self-supervised-learning-of-reliable","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","date":"2025-03-20","arxiv_id":"2503.16429","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":3,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["Pointcept/Pointcept","facebookresearch/sonata"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sonata-self-supervised-learning-of-reliable#ran","syntology_url":"https://syntology.ai/paper/2503.16429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16429"}}}},{"paper":"/paper/bfanet-revisiting-3d-semantic-segmentation","slug":"bfanet-revisiting-3d-semantic-segmentation","title":"BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis","date":"2025-03-16","arxiv_id":"2503.12539","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/any3dis-class-agnostic-3d-instance","slug":"any3dis-class-agnostic-3d-instance","title":"Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking","date":"2024-11-25","arxiv_id":"2411.16183","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/msta3d-multi-scale-twin-attention-for-3d-1","slug":"msta3d-multi-scale-twin-attention-for-3d-1","title":"MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation","date":"2024-11-04","arxiv_id":"2411.01781","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/arkit-labelmaker-a-new-scale-for-indoor-3d","slug":"arkit-labelmaker-a-new-scale-for-indoor-3d","title":"ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding","date":"2024-10-17","arxiv_id":"2410.13924","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["cvg/labelmaker"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/arkit-labelmaker-a-new-scale-for-indoor-3d#ran","syntology_url":"https://syntology.ai/paper/2410.13924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13924"}}}},{"paper":"/paper/mamba24-8d-enhancing-global-interaction-in","slug":"mamba24-8d-enhancing-global-interaction-in","title":"Pamba: Enhancing Global Interaction in Point Clouds via State Space Model","date":"2024-06-25","arxiv_id":"2406.17442","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/open-yolo-3d-towards-fast-and-accurate-open","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":7,"pointer_only_for_licence":11,"official":{"repos":["aminebdj/openyolo3d"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/open-yolo-3d-towards-fast-and-accurate-open#ran","syntology_url":"https://syntology.ai/paper/2406.02548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02548"}}}},{"paper":"/paper/lsk3dnet-towards-effective-and-efficient-3d","slug":"lsk3dnet-towards-effective-and-efficient-3d","title":"LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels","date":"2024-03-22","arxiv_id":"2403.15173","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/oa-cnns-omni-adaptive-sparse-cnns-for-3d","slug":"oa-cnns-omni-adaptive-sparse-cnns-for-3d","title":"OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation","date":"2024-03-21","arxiv_id":"2403.14418","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/odin-a-single-model-for-2d-and-3d-perception","slug":"odin-a-single-model-for-2d-and-3d-perception","title":"ODIN: A Single Model for 2D and 3D Segmentation","date":"2024-01-04","arxiv_id":"2401.02416","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":6,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ayushjain1144/odin"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/odin-a-single-model-for-2d-and-3d-perception#ran","syntology_url":"https://syntology.ai/paper/2401.02416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02416"}}}},{"paper":"/paper/open3dis-open-vocabulary-3d-instance","slug":"open3dis-open-vocabulary-3d-instance","title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","date":"2023-12-17","arxiv_id":"2312.10671","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["VinAIResearch/Open3DIS"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/open3dis-open-vocabulary-3d-instance#ran","syntology_url":"https://syntology.ai/paper/2312.10671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10671"}}}},{"paper":"/paper/point-transformer-v3-simpler-faster-stronger","slug":"point-transformer-v3-simpler-faster-stronger","title":"Point Transformer V3: Simpler, Faster, Stronger","date":"2023-12-15","arxiv_id":"2312.10035","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["Pointcept/Pointcept","pointcept/pointtransformerv3"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/point-transformer-v3-simpler-faster-stronger#ran","syntology_url":"https://syntology.ai/paper/2312.10035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10035"}}}},{"paper":"/paper/oneformer3d-one-transformer-for-unified-point","slug":"oneformer3d-one-transformer-for-unified-point","title":"OneFormer3D: One Transformer for Unified Point Cloud Segmentation","date":"2023-11-24","arxiv_id":"2311.14405","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ponderv2-pave-the-way-for-3d-foundataion","slug":"ponderv2-pave-the-way-for-3d-foundataion","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","date":"2023-10-12","arxiv_id":"2310.08586","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/openins3d-snap-and-lookup-for-3d-open","slug":"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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["Pointcept/OpenIns3D"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/openins3d-snap-and-lookup-for-3d-open#ran","syntology_url":"https://syntology.ai/paper/2309.00616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00616"}}}},{"paper":"/paper/towards-large-scale-3d-representation","slug":"towards-large-scale-3d-representation","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","date":"2023-08-18","arxiv_id":"2308.09718","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/openmask3d-open-vocabulary-3d-instance","slug":"openmask3d-open-vocabulary-3d-instance","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","date":"2023-06-23","arxiv_id":"2306.13631","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["OpenMask3D/openmask3d"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/openmask3d-open-vocabulary-3d-instance#ran","syntology_url":"https://syntology.ai/paper/2306.13631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.13631"}}}},{"paper":"/paper/octformer-octree-based-transformers-for-3d","slug":"octformer-octree-based-transformers-for-3d","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","date":"2023-05-04","arxiv_id":"2305.03045","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":3,"official":{"repos":["octree-nn/octformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/octformer-octree-based-transformers-for-3d#ran","syntology_url":"https://syntology.ai/paper/2305.03045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.03045"}}}},{"paper":"/paper/isbnet-a-3d-point-cloud-instance-segmentation","slug":"isbnet-a-3d-point-cloud-instance-segmentation","title":"ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution","date":"2023-03-01","arxiv_id":"2303.00246","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["VinAIResearch/ISBNet"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/isbnet-a-3d-point-cloud-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2303.00246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.00246"}}}},{"paper":"/paper/mask3d-for-3d-semantic-instance-segmentation","slug":"mask3d-for-3d-semantic-instance-segmentation","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","date":"2022-10-06","arxiv_id":"2210.03105","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":7,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["jonasschult/mask3d"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mask3d-for-3d-semantic-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2210.03105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03105"}}}},{"paper":"/paper/language-grounded-indoor-3d-semantic","slug":"language-grounded-indoor-3d-semantic","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","date":"2022-04-16","arxiv_id":"2204.07761","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["RozDavid/LanguageGroundedSemseg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-grounded-indoor-3d-semantic#ran","syntology_url":"https://syntology.ai/paper/2204.07761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.07761"}}}},{"paper":"/paper/exploring-data-efficient-3d-scene","slug":"exploring-data-efficient-3d-scene","title":"Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts","date":"2020-12-16","arxiv_id":"2012.09165","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/4d-spatio-temporal-convnets-minkowski","slug":"4d-spatio-temporal-convnets-minkowski","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","date":"2019-04-18","arxiv_id":"1904.08755","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["StanfordVL/MinkowskiEngine"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/4d-spatio-temporal-convnets-minkowski#ran","syntology_url":"https://syntology.ai/paper/1904.08755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08755"}}}}],"papers_where_code_ran":13,"papers_where_code_ran_first_page":"/dataset/scannet200/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/scannet200/papers/ran/1","json":"/dataset/scannet200/papers/ran/1.json","rows":13}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":13,"samples_harvested":105,"samples_ran":73,"samples_constructed":2,"samples_ran_checked":41,"samples_ran_instrument_failed":32,"samples_unverified":32,"pointer_only_for_licence":25,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":13,"papers_with_a_run_with_no_instrument_failure":10,"papers_where_every_run_was_an_instrument_failure":3,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":4,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/3d-open-vocabulary-instance-segmentation-on","since_archive":"/sota/3d-open-vocabulary-instance-segmentation-on#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/3d-instance-segmentation-on-scannet200","since_archive":"/sota/3d-instance-segmentation-on-scannet200#since-judged","papers_judged":3,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"f7fce5d6d10a5111b755d4f7bfdf38eae3845c7d69dc6bc02df58ae3d14cce7d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}