{"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_with_a_benchmark_row":[{"paper":"/paper/dino-in-the-room-leveraging-2d-foundation","title":"DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation","date":"2025-03-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sonata-self-supervised-learning-of-reliable","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","date":"2025-03-20","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":5,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bfanet-revisiting-3d-semantic-segmentation","title":"BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis","date":"2025-03-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/any3dis-class-agnostic-3d-instance","title":"Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking","date":"2024-11-25","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/msta3d-multi-scale-twin-attention-for-3d-1","title":"MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation","date":"2024-11-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/arkit-labelmaker-a-new-scale-for-indoor-3d","title":"ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding","date":"2024-10-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mamba24-8d-enhancing-global-interaction-in","title":"Pamba: Enhancing Global Interaction in Point Clouds via State Space Model","date":"2024-06-25","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":4,"samples_unverified":7,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lsk3dnet-towards-effective-and-efficient-3d","title":"LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels","date":"2024-03-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/oa-cnns-omni-adaptive-sparse-cnns-for-3d","title":"OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation","date":"2024-03-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/odin-a-single-model-for-2d-and-3d-perception","title":"ODIN: A Single Model for 2D and 3D Segmentation","date":"2024-01-04","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":3,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/open3dis-open-vocabulary-3d-instance","title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","date":"2023-12-17","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":8,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/point-transformer-v3-simpler-faster-stronger","title":"Point Transformer V3: Simpler, Faster, Stronger","date":"2023-12-15","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":7,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/oneformer3d-one-transformer-for-unified-point","title":"OneFormer3D: One Transformer for Unified Point Cloud Segmentation","date":"2023-11-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/openins3d-snap-and-lookup-for-3d-open","title":"OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation","date":"2023-09-01","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/towards-large-scale-3d-representation","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","date":"2023-08-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/openmask3d-open-vocabulary-3d-instance","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","date":"2023-06-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/octformer-octree-based-transformers-for-3d","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","date":"2023-05-04","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":2,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":2,"samples_unverified":17,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mask3d-for-3d-semantic-instance-segmentation","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","date":"2022-10-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":2,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/language-grounded-indoor-3d-semantic","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","date":"2022-04-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exploring-data-efficient-3d-scene","title":"Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts","date":"2020-12-16","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/4d-spatio-temporal-convnets-minkowski","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","date":"2019-04-18","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":13,"samples_harvested":105,"samples_ran":40,"samples_unverified":65,"pointer_only_for_licence":17,"papers_with_no_sample_that_ran":0,"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."}