{"url":"/task/3d-semantic-segmentation","name":"3D Semantic Segmentation","slug":"3d-semantic-segmentation","description_markdown":"**3D Semantic Segmentation** is a computer vision task that involves dividing a 3D point cloud or 3D mesh into semantically meaningful parts or regions. The goal of 3D semantic segmentation is to identify and label different objects and parts within a 3D scene, which can be used for applications such as robotics, autonomous driving, and augmented reality.","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":348,"papers_with_code":214,"benchmarks":19,"benchmark_tables_in_archive":19,"benchmark_tables_shown":19,"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":41,"subtasks":5,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","slug":"3d-semantic-segmentation-on-semantickitti","dataset":"SemanticKITTI","dataset_url":"/dataset/semantickitti","rows_in_archive":45,"metrics":["test mIoU","val mIoU","mIoU-1%"],"first_row_in_archive_order":{"model":"LSK3DNet","paper_title":"LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels","paper_url":"/paper/lsk3dnet-towards-effective-and-efficient-3d","paper_date":"2024-03-22","arxiv_id":"2403.15173","code_links":[{"title":"fengzicai/lsk3dnet","url":"https://github.com/fengzicai/lsk3dnet"}],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-scannet200","slug":"3d-semantic-segmentation-on-scannet200","dataset":"ScanNet200","dataset_url":"/dataset/scannet200","rows_in_archive":16,"metrics":["val mIoU","test mIoU"],"first_row_in_archive_order":{"model":"DITR","paper_title":"DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation","paper_url":"/paper/dino-in-the-room-leveraging-2d-foundation","paper_date":"2025-03-24","arxiv_id":"2503.18944","code_links":[{"title":"VisualComputingInstitute/DITR","url":"https://github.com/VisualComputingInstitute/DITR"}],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-dales","slug":"3d-semantic-segmentation-on-dales","dataset":"DALES","dataset_url":"/dataset/dales","rows_in_archive":9,"metrics":["mIoU","Overall Accuracy","Model size"],"first_row_in_archive_order":{"model":"KPConv","paper_title":"KPConv: Flexible and Deformable Convolution for Point Clouds","paper_url":"/paper/kpconv-flexible-and-deformable-convolution","paper_date":"2019-04-18","arxiv_id":"1904.08889","code_links":[{"title":"isl-org/Open3D-ML","url":"https://github.com/isl-org/Open3D-ML"},{"title":"HuguesTHOMAS/KPConv-PyTorch","url":"https://github.com/HuguesTHOMAS/KPConv-PyTorch"},{"title":"HuguesTHOMAS/KPConv","url":"https://github.com/HuguesTHOMAS/KPConv"},{"title":"ldkong1205/Robo3D","url":"https://github.com/ldkong1205/Robo3D"},{"title":"XuyangBai/KPConv.pytorch","url":"https://github.com/XuyangBai/KPConv.pytorch"},{"title":"plusmultiply/mprm","url":"https://github.com/plusmultiply/mprm"},{"title":"Arjun-NA/KPConv_for_DALES","url":"https://github.com/Arjun-NA/KPConv_for_DALES"},{"title":"Yacovitch/EyeNet","url":"https://github.com/Yacovitch/EyeNet"},{"title":"genglinliu/KPConv_Pytorch","url":"https://github.com/genglinliu/KPConv_Pytorch"},{"title":"JohnRomanelis/KPConv_torch_geometric","url":"https://github.com/JohnRomanelis/KPConv_torch_geometric"}],"syntology":{"n":12,"n_ran":5,"n_unverified":7,"n_pointer_only":3}}},{"leaderboard":"/sota/3d-semantic-segmentation-on-kitti-360","slug":"3d-semantic-segmentation-on-kitti-360","dataset":"KITTI-360","dataset_url":"/dataset/kitti-360","rows_in_archive":8,"metrics":["miou","mIoU Category","miou Val","Model size"],"first_row_in_archive_order":{"model":"DeepViewAgg","paper_title":"Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation","paper_url":"/paper/learning-multi-view-aggregation-in-the-wild","paper_date":"2022-04-15","arxiv_id":"2204.07548","code_links":[{"title":"drprojects/deepviewagg","url":"https://github.com/drprojects/deepviewagg"}],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-scannet-1","slug":"3d-semantic-segmentation-on-scannet-1","dataset":"ScanNet++","dataset_url":"/dataset/scannet-1","rows_in_archive":8,"metrics":["Top-1 IoU","Top-3 IoU"],"first_row_in_archive_order":{"model":"DITR","paper_title":"DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation","paper_url":"/paper/dino-in-the-room-leveraging-2d-foundation","paper_date":"2025-03-24","arxiv_id":"2503.18944","code_links":[{"title":"VisualComputingInstitute/DITR","url":"https://github.com/VisualComputingInstitute/DITR"}],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-sensaturban","slug":"3d-semantic-segmentation-on-sensaturban","dataset":"SensatUrban","dataset_url":"/dataset/sensaturban","rows_in_archive":8,"metrics":["mIoU","oAcc"],"first_row_in_archive_order":{"model":"LCPFormer","paper_title":"LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers","paper_url":"/paper/lcpformer-towards-effective-3d-point-cloud","paper_date":"2022-10-23","arxiv_id":"2210.12755","code_links":[{"title":"zhh6425/LocalContextPropagation","url":"https://github.com/zhh6425/LocalContextPropagation"}],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-toronto-3d","slug":"3d-semantic-segmentation-on-toronto-3d","dataset":"Toronto-3D","dataset_url":"/dataset/toronto-3d","rows_in_archive":7,"metrics":["OA","mIoU"],"first_row_in_archive_order":{"model":"SCF-Net","paper_title":"SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation","paper_url":"/paper/scf-net-learning-spatial-contextual-features","paper_date":"2021-06-19","arxiv_id":null,"code_links":[{"title":"leofansq/SCF-Net","url":"https://github.com/leofansq/SCF-Net"}],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-partnet","slug":"3d-semantic-segmentation-on-partnet","dataset":"PartNet","dataset_url":"/dataset/partnet","rows_in_archive":6,"metrics":["mIOU"],"first_row_in_archive_order":{"model":"CSN","paper_title":"Cross-Shape Attention for Part Segmentation of 3D Point Clouds","paper_url":"/paper/cross-shape-graph-convolutional-networks","paper_date":"2020-03-20","arxiv_id":"2003.09053","code_links":[{"title":"marios2019/CSN","url":"https://github.com/marios2019/CSN"}],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-s3dis","slug":"3d-semantic-segmentation-on-s3dis","dataset":"S3DIS","dataset_url":"/dataset/s3dis","rows_in_archive":6,"metrics":["mIoU (Area-5)","mIoU (6-Fold)","mAcc"],"first_row_in_archive_order":{"model":"OneFormer3D","paper_title":"OneFormer3D: One Transformer for Unified Point Cloud Segmentation","paper_url":"/paper/oneformer3d-one-transformer-for-unified-point","paper_date":"2023-11-24","arxiv_id":"2311.14405","code_links":[{"title":"oneformer3d/oneformer3d","url":"https://github.com/oneformer3d/oneformer3d"}],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-scribblekitti","slug":"3d-semantic-segmentation-on-scribblekitti","dataset":"ScribbleKITTI","dataset_url":"/dataset/scribblekitti","rows_in_archive":6,"metrics":["mIoU","mIoU-1%"],"first_row_in_archive_order":{"model":"IGNet","paper_title":"2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation","paper_url":"/paper/2d-feature-distillation-for-weakly-and-semi","paper_date":"2023-11-27","arxiv_id":"2311.15605","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-stpls3d","slug":"3d-semantic-segmentation-on-stpls3d","dataset":"STPLS3D","dataset_url":"/dataset/stpls3d","rows_in_archive":6,"metrics":["mIOU"],"first_row_in_archive_order":{"model":"KpConv","paper_title":"KPConv: Flexible and Deformable Convolution for Point Clouds","paper_url":"/paper/kpconv-flexible-and-deformable-convolution","paper_date":"2019-04-18","arxiv_id":"1904.08889","code_links":[{"title":"isl-org/Open3D-ML","url":"https://github.com/isl-org/Open3D-ML"},{"title":"HuguesTHOMAS/KPConv-PyTorch","url":"https://github.com/HuguesTHOMAS/KPConv-PyTorch"},{"title":"HuguesTHOMAS/KPConv","url":"https://github.com/HuguesTHOMAS/KPConv"},{"title":"ldkong1205/Robo3D","url":"https://github.com/ldkong1205/Robo3D"},{"title":"XuyangBai/KPConv.pytorch","url":"https://github.com/XuyangBai/KPConv.pytorch"},{"title":"plusmultiply/mprm","url":"https://github.com/plusmultiply/mprm"},{"title":"Arjun-NA/KPConv_for_DALES","url":"https://github.com/Arjun-NA/KPConv_for_DALES"},{"title":"Yacovitch/EyeNet","url":"https://github.com/Yacovitch/EyeNet"},{"title":"genglinliu/KPConv_Pytorch","url":"https://github.com/genglinliu/KPConv_Pytorch"},{"title":"JohnRomanelis/KPConv_torch_geometric","url":"https://github.com/JohnRomanelis/KPConv_torch_geometric"}],"syntology":{"n":12,"n_ran":5,"n_unverified":7,"n_pointer_only":3}}},{"leaderboard":"/sota/3d-semantic-segmentation-on-rellis-3d-dataset","slug":"3d-semantic-segmentation-on-rellis-3d-dataset","dataset":"RELLIS-3D Dataset","dataset_url":"/dataset/rellis-3d","rows_in_archive":4,"metrics":["Mean IoU (class)"],"first_row_in_archive_order":{"model":"Cylinder3D","paper_title":"Comparison of lidar semantic segmentation performance on the structured SemanticKITTI and off-road RELLIS-3D datasets","paper_url":"/paper/comparison-of-lidar-semantic-segmentation","paper_date":"2024-08-20","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-wildscenes","slug":"3d-semantic-segmentation-on-wildscenes","dataset":"WildScenes","dataset_url":"/dataset/wildscenes","rows_in_archive":4,"metrics":["mIoU","mIoU (Temporal DA)","mIoU (Env DA)"],"first_row_in_archive_order":{"model":"Cylinder3D","paper_title":"Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation","paper_url":"/paper/cylinder3d-an-effective-3d-framework-for","paper_date":"2020-08-04","arxiv_id":"2008.01550","code_links":[{"title":"xinge008/Cylinder3D","url":"https://github.com/xinge008/Cylinder3D"},{"title":"hongfz16/DS-Net","url":"https://github.com/hongfz16/DS-Net"},{"title":"L-Reichardt/Cylinder3D-updated-CUDA","url":"https://github.com/L-Reichardt/Cylinder3D-updated-CUDA"}],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-nuscenes","slug":"3d-semantic-segmentation-on-nuscenes","dataset":"nuScenes","dataset_url":"/dataset/nuscenes","rows_in_archive":3,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"PTv2","paper_title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","paper_url":"/paper/point-transformer-v2-grouped-vector-attention","paper_date":"2022-10-11","arxiv_id":"2210.05666","code_links":[{"title":"Pointcept/Pointcept","url":"https://github.com/Pointcept/Pointcept"},{"title":"Pointcept/PointTransformerV2","url":"https://github.com/Pointcept/PointTransformerV2"}],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-opentrench3d","slug":"3d-semantic-segmentation-on-opentrench3d","dataset":"OpenTrench3D","dataset_url":"/dataset/opentrench3d","rows_in_archive":3,"metrics":["mIoU","mAcc","Model Size"],"first_row_in_archive_order":{"model":"PointVector-XL","paper_title":"PointVector: A Vector Representation In Point Cloud Analysis","paper_url":"/paper/point-is-a-vector-a-feature-representation-in","paper_date":"2022-05-21","arxiv_id":"2205.10528","code_links":[{"title":"guochengqian/openpoints","url":"https://github.com/guochengqian/openpoints/blob/master/models/backbone/pointvector.py"}],"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-semantic-segmentation-on-hypersim","slug":"3d-semantic-segmentation-on-hypersim","dataset":"Hypersim","dataset_url":"/dataset/hypersim","rows_in_archive":2,"metrics":["mIoU","mIoU (test)"],"first_row_in_archive_order":{"model":"PanopticNDT (10cm)","paper_title":"PanopticNDT: Efficient and Robust Panoptic Mapping","paper_url":"/paper/panopticndt-efficient-and-robust-panoptic","paper_date":"2023-09-24","arxiv_id":"2309.13635","code_links":[{"title":"tui-nicr/emsanet","url":"https://github.com/tui-nicr/emsanet"},{"title":"tui-nicr/panoptic-mapping","url":"https://github.com/tui-nicr/panoptic-mapping"},{"title":"tui-nicr/nicr-scene-analysis-datasets","url":"https://github.com/tui-nicr/nicr-scene-analysis-datasets"},{"title":"tui-nicr/emsaformer","url":"https://github.com/tui-nicr/emsaformer"}],"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-semantic-segmentation-on-waymo-open","slug":"3d-semantic-segmentation-on-waymo-open","dataset":"Waymo Open Dataset","dataset_url":"/dataset/waymo-open-dataset","rows_in_archive":2,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"DITR","paper_title":"DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation","paper_url":"/paper/dino-in-the-room-leveraging-2d-foundation","paper_date":"2025-03-24","arxiv_id":"2503.18944","code_links":[{"title":"VisualComputingInstitute/DITR","url":"https://github.com/VisualComputingInstitute/DITR"}],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-3d-platelet-em","slug":"3d-semantic-segmentation-on-3d-platelet-em","dataset":"3D Platelet EM","dataset_url":"/dataset/3d-platelet-em","rows_in_archive":1,"metrics":["Mean IoU (test)"],"first_row_in_archive_order":{"model":"2D–3D + 3 × 3 × 3","paper_title":"Dense cellular segmentation for EM using 2D–3D neural network ensembles","paper_url":"/paper/dense-cellular-segmentation-for-em-using-2d","paper_date":"2021-01-28","arxiv_id":null,"code_links":[{"title":"leapmanlab/examples","url":"https://github.com/leapmanlab/examples"}],"syntology":null}},{"leaderboard":"/sota/3d-semantic-segmentation-on-eclair","slug":"3d-semantic-segmentation-on-eclair","dataset":"ECLAIR","dataset_url":"/dataset/eclair","rows_in_archive":1,"metrics":["F1","Mean IoU"],"first_row_in_archive_order":{"model":"Res16UNet14C","paper_title":"ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic Segmentation","paper_url":"/paper/eclair-a-high-fidelity-aerial-lidar-dataset","paper_date":"2024-04-16","arxiv_id":"2404.10699","code_links":[{"title":"sharpershape/eclair-dataset","url":"https://github.com/sharpershape/eclair-dataset"}],"syntology":null}}],"datasets":[{"url":"/dataset/nuscenes","name":"nuScenes","full_name":"","num_papers_in_archive":2139},{"url":"/dataset/semantickitti","name":"SemanticKITTI","full_name":"","num_papers_in_archive":669},{"url":"/dataset/s3dis","name":"S3DIS","full_name":"Stanford 3D Indoor Scene Dataset (S3DIS)","num_papers_in_archive":488},{"url":"/dataset/waymo-open-dataset","name":"Waymo Open Dataset","full_name":"","num_papers_in_archive":481},{"url":"/dataset/kitti-360","name":"KITTI-360","full_name":"","num_papers_in_archive":246},{"url":"/dataset/partnet","name":"PartNet","full_name":"","num_papers_in_archive":156},{"url":"/dataset/hypersim","name":"Hypersim","full_name":"","num_papers_in_archive":108},{"url":"/dataset/amos","name":"AMOS","full_name":"","num_papers_in_archive":105},{"url":"/dataset/semanticposs","name":"SemanticPOSS","full_name":"","num_papers_in_archive":71},{"url":"/dataset/rellis-3d","name":"RELLIS-3D","full_name":null,"num_papers_in_archive":57},{"url":"/dataset/scannet200","name":"ScanNet200","full_name":"","num_papers_in_archive":45},{"url":"/dataset/3r-scan","name":"3RScan","full_name":"","num_papers_in_archive":44},{"url":"/dataset/stpls3d","name":"STPLS3D","full_name":"","num_papers_in_archive":36},{"url":"/dataset/nuscenes-c","name":"nuScenes-C","full_name":"","num_papers_in_archive":33},{"url":"/dataset/sensaturban","name":"SensatUrban","full_name":"","num_papers_in_archive":28},{"url":"/dataset/dales","name":"DALES","full_name":"DALES: A Large-scale Aerial LiDAR Data Set for Semantic Segmentation","num_papers_in_archive":26},{"url":"/dataset/semantickitti-c","name":"SemanticKITTI-C","full_name":"","num_papers_in_archive":26},{"url":"/dataset/scannet-1","name":"ScanNet++","full_name":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","num_papers_in_archive":25},{"url":"/dataset/toronto-3d","name":"Toronto-3D","full_name":null,"num_papers_in_archive":24},{"url":"/dataset/synlidar","name":"SynLiDAR","full_name":"","num_papers_in_archive":20},{"url":"/dataset/scribblekitti","name":"ScribbleKITTI","full_name":"","num_papers_in_archive":19},{"url":"/dataset/paris-lille-3d","name":"Paris-Lille-3D","full_name":"","num_papers_in_archive":15},{"url":"/dataset/hm3dsem","name":"HM3DSem","full_name":"","num_papers_in_archive":13},{"url":"/dataset/semanticstf","name":"SemanticSTF","full_name":"","num_papers_in_archive":12},{"url":"/dataset/wildscenes","name":"WildScenes","full_name":"","num_papers_in_archive":12},{"url":"/dataset/buildingnet","name":"BuildingNet","full_name":"","num_papers_in_archive":11},{"url":"/dataset/dttd2","name":"DTTD-Mobile","full_name":"","num_papers_in_archive":8},{"url":"/dataset/for-instance","name":"FOR-instance","full_name":"FOR-instance: a UAV laser scanning benchmark dataset for semantic and instance segmentation of individual trees","num_papers_in_archive":7},{"url":"/dataset/kits19","name":"KiTS19","full_name":"The 2019 Kidney and Kidney Tumor Segmentation Challenge","num_papers_in_archive":7},{"url":"/dataset/lidar-mos","name":"LiDAR-MOS","full_name":"LiDAR-based Moving Object Segmentation","num_papers_in_archive":6},{"url":"/dataset/wod-c","name":"WOD-C","full_name":"","num_papers_in_archive":5},{"url":"/dataset/swiss3dcities","name":"Swiss3DCities","full_name":"","num_papers_in_archive":4},{"url":"/dataset/arch2s","name":"ARCH2S","full_name":"Dataset, Benchmark for Learning Exterior Architectural Structures from Point Clouds","num_papers_in_archive":3},{"url":"/dataset/opentrench3d","name":"OpenTrench3D","full_name":"","num_papers_in_archive":3},{"url":"/dataset/3d-platelet-em","name":"3D Platelet EM","full_name":"Platelet Electron Microscopy","num_papers_in_archive":2},{"url":"/dataset/arkit-labelmaker","name":"ARKit LabelMaker","full_name":"","num_papers_in_archive":1},{"url":"/dataset/eclair","name":"ECLAIR","full_name":"ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic Segmentation","num_papers_in_archive":1},{"url":"/dataset/gf-pa66-3d-xct-composite-material-3d","name":"GF-PA66 3D XCT","full_name":"Glass fiber-reinforced polyamide 66 (GF-PA66) 3D X-ray Computed Tomography (XCT))","num_papers_in_archive":1},{"url":"/dataset/gf-pa66-3d-xct-latest","name":"GF-PA66 3D XCT (latest)","full_name":"Glass fiber-reinforced polyamide 66 3D X-ray Computed Tomography","num_papers_in_archive":1},{"url":"/dataset/hepic","name":"HePIC 🏛️","full_name":"","num_papers_in_archive":1},{"url":"/dataset/inlut3d","name":"InLUT3D","full_name":"Indoor Lodz University of Technology Point Cloud Dataset","num_papers_in_archive":0}],"subtasks":[{"url":"/task/3d-point-cloud-part-segmentation","name":"3D Point Cloud Part Segmentation"},{"url":"/task/furniture-segmentation","name":"furniture segmentation"},{"url":"/task/real-time-3d-semantic-segmentation","name":"Real-Time 3D Semantic Segmentation"},{"url":"/task/robust-3d-semantic-segmentation","name":"Robust 3D Semantic Segmentation"},{"url":"/task/unsupervised-3d-semantic-segmentation","name":"Unsupervised 3D Semantic Segmentation"}],"parent_tasks":[{"url":"/task/semantic-segmentation","name":"Semantic Segmentation"}],"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":30,"of":214,"tagged_in_all":348,"items":[{"url":"/paper/pointnet-deep-learning-on-point-sets-for-3d","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","date":"2016-12-02","arxiv_id":"1612.00593","repositories_listed":110,"syntology":{"n":164,"n_ran":89,"n_unverified":75,"n_pointer_only":90}},{"url":"/paper/pointnet-deep-hierarchical-feature-learning","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","date":"2017-06-07","arxiv_id":"1706.02413","repositories_listed":68,"syntology":{"n":67,"n_ran":36,"n_unverified":31,"n_pointer_only":26}},{"url":"/paper/point-transformer-1","title":"Point Transformer","date":"2020-12-16","arxiv_id":"2012.09164","repositories_listed":24,"syntology":null},{"url":"/paper/dynamic-graph-cnn-for-learning-on-point","title":"Dynamic Graph CNN for Learning on Point Clouds","date":"2018-01-24","arxiv_id":"1801.07829","repositories_listed":21,"syntology":{"n":44,"n_ran":16,"n_unverified":28,"n_pointer_only":31}},{"url":"/paper/kpconv-flexible-and-deformable-convolution","title":"KPConv: Flexible and Deformable Convolution for Point Clouds","date":"2019-04-18","arxiv_id":"1904.08889","repositories_listed":10,"syntology":{"n":12,"n_ran":5,"n_unverified":7,"n_pointer_only":3}},{"url":"/paper/191111236","title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds","date":"2019-11-25","arxiv_id":"1911.11236","repositories_listed":9,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/4d-spatio-temporal-convnets-minkowski","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","date":"2019-04-18","arxiv_id":"1904.08755","repositories_listed":8,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/searching-efficient-3d-architectures-with","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","date":"2020-07-31","arxiv_id":"2007.16100","repositories_listed":6,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/3d-semantic-segmentation-with-submanifold","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","date":"2017-11-28","arxiv_id":"1711.10275","repositories_listed":6,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/salsanext-fast-semantic-segmentation-of-lidar","title":"SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving","date":"2020-03-07","arxiv_id":"2003.03653","repositories_listed":5,"syntology":{"n":11,"n_ran":4,"n_unverified":7,"n_pointer_only":1}},{"url":"/paper/the-state-of-the-art-in-kidney-and-kidney","title":"The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge","date":"2019-12-02","arxiv_id":"1912.01054","repositories_listed":5,"syntology":{"n":13,"n_ran":4,"n_unverified":9,"n_pointer_only":4}},{"url":"/paper/a-dataset-for-semantic-segmentation-of-point","title":"SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences","date":"2019-04-02","arxiv_id":"1904.01416","repositories_listed":5,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"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","date":"2018-12-06","arxiv_id":"1812.02713","repositories_listed":5,"syntology":null},{"url":"/paper/squeezeseg-convolutional-neural-nets-with","title":"SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud","date":"2017-10-19","arxiv_id":"1710.07368","repositories_listed":5,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/panopticndt-efficient-and-robust-panoptic","title":"PanopticNDT: Efficient and Robust Panoptic Mapping","date":"2023-09-24","arxiv_id":"2309.13635","repositories_listed":4,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/octformer-octree-based-transformers-for-3d","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","date":"2023-05-04","arxiv_id":"2305.03045","repositories_listed":4,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/stpls3d-a-large-scale-synthetic-and-real","title":"STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset","date":"2022-03-17","arxiv_id":"2203.09065","repositories_listed":4,"syntology":{"n":23,"n_ran":4,"n_unverified":19,"n_pointer_only":3}},{"url":"/paper/mix3d-out-of-context-data-augmentation-for-3d","title":"Mix3D: Out-of-Context Data Augmentation for 3D Scenes","date":"2021-10-05","arxiv_id":"2110.02210","repositories_listed":4,"syntology":{"n":25,"n_ran":4,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/shape-aware-semi-supervised-3d-semantic","title":"Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images","date":"2020-07-21","arxiv_id":"2007.10732","repositories_listed":4,"syntology":null},{"url":"/paper/polarnet-an-improved-grid-representation-for","title":"PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation","date":"2020-03-31","arxiv_id":"2003.14032","repositories_listed":4,"syntology":{"n":11,"n_ran":9,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/deepgcns-making-gcns-go-as-deep-as-cnns","title":"DeepGCNs: Making GCNs Go as Deep as CNNs","date":"2019-10-15","arxiv_id":"1910.06849","repositories_listed":4,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":1}},{"url":"/paper/point-voxel-cnn-for-efficient-3d-deep","title":"Point-Voxel CNN for Efficient 3D Deep Learning","date":"2019-07-08","arxiv_id":"1907.03739","repositories_listed":4,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/on-deep-learning-for-geometric-and-semantic","title":"On Deep Learning for Geometric and Semantic Scene Understanding Using On-Vehicle 3D LiDAR","date":"2024-11-01","arxiv_id":"2411.00600","repositories_listed":3,"syntology":null},{"url":"/paper/point-transformer-v3-simpler-faster-stronger","title":"Point Transformer V3: Simpler, Faster, Stronger","date":"2023-12-15","arxiv_id":"2312.10035","repositories_listed":3,"syntology":{"n":11,"n_ran":7,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/towards-robust-robot-3d-perception-in-urban","title":"Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset","date":"2023-09-24","arxiv_id":"2309.13549","repositories_listed":3,"syntology":null},{"url":"/paper/cenet-toward-concise-and-efficient-lidar","title":"CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving","date":"2022-07-26","arxiv_id":"2207.12691","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/pointnext-revisiting-pointnet-with-improved","title":"PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies","date":"2022-06-09","arxiv_id":"2206.04670","repositories_listed":3,"syntology":{"n":17,"n_ran":7,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/scribble-supervised-lidar-semantic","title":"Scribble-Supervised LiDAR Semantic Segmentation","date":"2022-03-16","arxiv_id":"2203.08537","repositories_listed":3,"syntology":null},{"url":"/paper/swin-unetr-swin-transformers-for-semantic","title":"Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images","date":"2022-01-04","arxiv_id":"2201.01266","repositories_listed":3,"syntology":null},{"url":"/paper/cross-modal-learning-for-domain-adaptation-in","title":"Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation","date":"2021-01-18","arxiv_id":"2101.07253","repositories_listed":3,"syntology":null}],"syntology_records":22,"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"}}