{"url":"/sota/semantic-segmentation-on-s3dis","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"S3DIS","url":"/dataset/s3dis"},"category":"Computer Vision","categories":["Computer Code","Computer Vision","Medical","Robots"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Mean IoU","mAcc","oAcc","FLOPs","Number of params","mIoU","Params (M)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Mean IoU":"higher","mAcc":null,"oAcc":null,"FLOPs":"lower","Number of params":"lower","mIoU":null,"Params (M)":"lower"}},"counts":{"rows":54,"rows_with_code":53,"rows_with_paper_page":54,"rows_dated":54,"rows_using_additional_data":5},"rows":[{"rank_in_archive_order":1,"model":"Sonata + PTv3","metrics":{"Mean IoU":"82.3","Number of params":"128M","mAcc":"89.9","oAcc":"93.3"},"uses_additional_data":true,"paper_date":"2025-03-20","paper":"/paper/sonata-self-supervised-learning-of-reliable","paper_url":"https://arxiv.org/abs/2503.16429v1","paper_title":"Sonata: Self-Supervised Learning of Reliable Point Representations","code":"https://github.com/Pointcept/Pointcept","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":14,"n_samples":19,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"PTv3 + PPT","metrics":{"Mean IoU":"80.8","Number of params":"24.1M","mAcc":"87.7","oAcc":"92.6"},"uses_additional_data":true,"paper_date":"2023-12-15","paper":"/paper/point-transformer-v3-simpler-faster-stronger","paper_url":"https://arxiv.org/abs/2312.10035v2","paper_title":"Point Transformer V3: Simpler, Faster, Stronger","code":"https://github.com/Pointcept/Pointcept","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"PonderV2 + SparseUNet","metrics":{"Mean IoU":"79.9","mAcc":"86.5","oAcc":"92.5"},"uses_additional_data":true,"paper_date":"2023-10-12","paper":"/paper/ponderv2-pave-the-way-for-3d-foundataion","paper_url":"https://arxiv.org/abs/2310.08586v3","paper_title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","code":"https://github.com/OpenGVLab/PonderV2","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Swin3D-L","metrics":{"Mean IoU":"79.8","Number of params":"N/A","mAcc":"88.0","oAcc":"92.4"},"uses_additional_data":true,"paper_date":"2023-04-14","paper":"/paper/swin3d-a-pretrained-transformer-backbone-for","paper_url":"https://arxiv.org/abs/2304.06906v3","paper_title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","code":"https://github.com/Pointcept/Pointcept","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"PointVector-XL","metrics":{"Mean IoU":"78.4","Params (M)":"24.1","mAcc":"86.1","oAcc":"91.9"},"uses_additional_data":false,"paper_date":"2022-05-21","paper":"/paper/point-is-a-vector-a-feature-representation-in","paper_url":"https://arxiv.org/abs/2205.10528v3","paper_title":"PointVector: A Vector Representation In Point Cloud Analysis","code":"https://github.com/guochengqian/openpoints/blob/master/models/backbone/pointvector.py","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"PPT + SparseUNet","metrics":{"Mean IoU":"78.1","Number of params":"N/A","mAcc":"85.4","oAcc":"92.2"},"uses_additional_data":true,"paper_date":"2023-08-18","paper":"/paper/towards-large-scale-3d-representation","paper_url":"https://arxiv.org/abs/2308.09718v2","paper_title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","code":"https://github.com/Pointcept/Pointcept","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"WindowNorm+StratifiedTransformer","metrics":{"Mean IoU":"77.6","Number of params":"8.2M","Params (M)":"8.2","mAcc":"85.8","oAcc":"91.7"},"uses_additional_data":false,"paper_date":"2022-12-05","paper":"/paper/window-normalization-enhancing-point-cloud","paper_url":"https://arxiv.org/abs/2212.02287v1","paper_title":"Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities","code":"https://github.com/DBDXSS/Window-Normalization","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"EQ-Net","metrics":{"Mean IoU":"77.5","Number of params":"N/A"},"uses_additional_data":false,"paper_date":"2022-03-02","paper":"/paper/a-unified-query-based-paradigm-for-point","paper_url":"https://arxiv.org/abs/2203.01252v3","paper_title":"A Unified Query-based Paradigm for Point Cloud Understanding","code":"https://github.com/dvlab-research/deepvision3d","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"PointMetaBase-XXL","metrics":{"FLOPs":"11.0G","Mean IoU":"77.0","Number of params":"19.7M","Params (M)":"19.7","oAcc":"91.3"},"uses_additional_data":false,"paper_date":"2022-11-26","paper":"/paper/meta-architecure-for-point-cloud-analysis","paper_url":"https://arxiv.org/abs/2211.14462v2","paper_title":"Meta Architecture for Point Cloud Analysis","code":"https://github.com/linhaojia13/pointmetabase","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"Superpoint Transformer","metrics":{"Mean IoU":"76.0","Number of params":"0.212M","Params (M)":"0.212","mAcc":"85.8","mIoU":"76.0","oAcc":"90.4"},"uses_additional_data":false,"paper_date":"2023-06-13","paper":"/paper/efficient-3d-semantic-segmentation-with-1","paper_url":"https://arxiv.org/abs/2306.08045v2","paper_title":"Efficient 3D Semantic Segmentation with Superpoint Transformer","code":"https://github.com/drprojects/superpoint_transformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"SuperCluster","metrics":{"Mean IoU":"75.3","Number of params":"0.21M","Params (M)":"0.21"},"uses_additional_data":false,"paper_date":"2024-01-12","paper":"/paper/scalable-3d-panoptic-segmentation-with","paper_url":"https://arxiv.org/abs/2401.06704v2","paper_title":"Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering","code":"https://github.com/drprojects/superpoint_transformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"PointNeXt-XL","metrics":{"FLOPs":"84.8G","Mean IoU":"74.9","Number of params":"41.6M","Params (M)":"41.6","mAcc":"83.0","oAcc":"90.3"},"uses_additional_data":false,"paper_date":"2022-06-09","paper":"/paper/pointnext-revisiting-pointnet-with-improved","paper_url":"https://arxiv.org/abs/2206.04670v2","paper_title":"PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies","code":"https://github.com/guochengqian/pointnext","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":10,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"DeepViewAgg","metrics":{"Mean IoU":"74.7","Number of params":"41.2M","Params (M)":"41.2","mAcc":"83.8","oAcc":"90.1"},"uses_additional_data":false,"paper_date":"2022-04-15","paper":"/paper/learning-multi-view-aggregation-in-the-wild","paper_url":"https://arxiv.org/abs/2204.07548v2","paper_title":"Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation","code":"https://github.com/drprojects/deepviewagg","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"RepSurf-U","metrics":{"FLOPs":"1.04G","Mean IoU":"74.3","Number of params":"0.97M","Params (M)":"0.97","mAcc":"82.6","oAcc":"90.8"},"uses_additional_data":false,"paper_date":"2022-05-11","paper":"/paper/surface-representation-for-point-clouds","paper_url":"https://arxiv.org/abs/2205.05740v2","paper_title":"Surface Representation for Point Clouds","code":"https://github.com/hancyran/RepSurf","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":13,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"WindowNorm+PointTransformer","metrics":{"Mean IoU":"74.1","Number of params":"8.0M","Params (M)":"8","mAcc":"82.5","oAcc":"90.2"},"uses_additional_data":false,"paper_date":"2022-12-05","paper":"/paper/window-normalization-enhancing-point-cloud","paper_url":"https://arxiv.org/abs/2212.02287v1","paper_title":"Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities","code":"https://github.com/DBDXSS/Window-Normalization","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"PointNeXt-L","metrics":{"FLOPs":"15.2G","Mean IoU":"73.9","Number of params":"7.1M","Params (M)":"7.1","mAcc":"82.2","oAcc":"89.9"},"uses_additional_data":false,"paper_date":"2022-06-09","paper":"/paper/pointnext-revisiting-pointnet-with-improved","paper_url":"https://arxiv.org/abs/2206.04670v2","paper_title":"PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies","code":"https://github.com/guochengqian/pointnext","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":10,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"PointTransformer","metrics":{"Mean IoU":"73.5","Number of params":"7.8M","Params (M)":"7.8","mAcc":"81.9","oAcc":"90.2"},"uses_additional_data":false,"paper_date":"2020-12-16","paper":"/paper/point-transformer-1","paper_url":"https://arxiv.org/abs/2012.09164v2","paper_title":"Point Transformer","code":"https://github.com/Pointcept/Pointcept","n_code_links":24,"syntology":null},{"rank_in_archive_order":18,"model":"CBL","metrics":{"Mean IoU":"73.1","Number of params":"N/A","mAcc":"79.4","oAcc":"89.6"},"uses_additional_data":false,"paper_date":"2022-03-10","paper":"/paper/contrastive-boundary-learning-for-point-cloud","paper_url":"https://arxiv.org/abs/2203.05272v2","paper_title":"Contrastive Boundary Learning for Point Cloud Segmentation","code":"https://github.com/liyaotang/contrastboundary","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"BAAF-Net","metrics":{"Mean IoU":"72.2","Number of params":"N/A","mAcc":"83.1","oAcc":"88.9"},"uses_additional_data":false,"paper_date":"2021-03-12","paper":"/paper/semantic-segmentation-for-real-point-cloud","paper_url":"https://arxiv.org/abs/2103.07074v2","paper_title":"Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion","code":"https://github.com/ShiQiu0419/BAAF-Net","n_code_links":2,"syntology":null},{"rank_in_archive_order":20,"model":"SCF-Net","metrics":{"Mean IoU":"71.6","Number of params":"N/A","mAcc":"82.7","oAcc":"88.4"},"uses_additional_data":false,"paper_date":"2021-06-19","paper":"/paper/scf-net-learning-spatial-contextual-features","paper_url":"http://openaccess.thecvf.com//content/CVPR2021/html/Fan_SCF-Net_Learning_Spatial_Contextual_Features_for_Large-Scale_Point_Cloud_Segmentation_CVPR_2021_paper.html","paper_title":"SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation","code":"https://github.com/leofansq/SCF-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"Feature Geometric Net (FG-Net)","metrics":{"Mean IoU":"70.8","Number of params":"N/A","mAcc":"82.9","oAcc":"88.2"},"uses_additional_data":false,"paper_date":"2020-12-17","paper":"/paper/fg-net-fast-large-scale-lidar-point","paper_url":"https://arxiv.org/abs/2012.09439v2","paper_title":"FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling","code":"https://github.com/KangchengLiu/Feature-Geometric-Net-FG-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"RPNet","metrics":{"Mean IoU":"70.8","Number of params":"N/A"},"uses_additional_data":false,"paper_date":"2021-08-27","paper":"/paper/learning-inner-group-relations-on-point","paper_url":"https://arxiv.org/abs/2108.12468v1","paper_title":"Learning Inner-Group Relations on Point Clouds","code":"https://github.com/hancyran/RPNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"KPConv","metrics":{"Mean IoU":"70.6","Number of params":"14.1M","Params (M)":"14.1","mAcc":"79.1"},"uses_additional_data":false,"paper_date":"2019-04-18","paper":"/paper/kpconv-flexible-and-deformable-convolution","paper_url":"https://arxiv.org/abs/1904.08889v2","paper_title":"KPConv: Flexible and Deformable Convolution for Point Clouds","code":"https://github.com/isl-org/Open3D-ML","n_code_links":10,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":3}},{"rank_in_archive_order":24,"model":"KPConv","metrics":{"Mean IoU":"70.6","Number of params":"14.1M","Params (M)":"14.1"},"uses_additional_data":false,"paper_date":"2020-12-16","paper":"/paper/point-transformer-1","paper_url":"https://arxiv.org/abs/2012.09164v2","paper_title":"Point Transformer","code":"https://github.com/Pointcept/Pointcept","n_code_links":24,"syntology":null},{"rank_in_archive_order":25,"model":"FastPointTrans. (small)","metrics":{"Mean IoU":"70.3","Number of params":"N/A"},"uses_additional_data":false,"paper_date":"2021-12-09","paper":"/paper/fast-point-transformer","paper_url":"https://arxiv.org/abs/2112.04702v2","paper_title":"Fast Point Transformer","code":"https://github.com/POSTECH-CVLab/FastPointTransformer","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"MuGNet","metrics":{"Mean IoU":"69.8","Number of params":"N/A","oAcc":"88.5"},"uses_additional_data":false,"paper_date":"2020-11-16","paper":"/paper/mugnet-multi-resolution-graph-neural-network","paper_url":"https://arxiv.org/abs/2009.08924?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%253A+arxiv%252FQSXk+%2528ExcitingAds%2521+cs+updates+on+arXiv.org%2529","paper_title":"MuGNet: Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation","code":"https://github.com/liuyuex97/MuGNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"PointASNL","metrics":{"Mean IoU":"68.7","Number of params":"N/A","mAcc":"79.0","oAcc":"88.8"},"uses_additional_data":false,"paper_date":"2020-03-01","paper":"/paper/pointasnl-robust-point-clouds-processing","paper_url":"https://arxiv.org/abs/2003.00492v3","paper_title":"PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling","code":"https://github.com/yanx27/PointASNL","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"SSP+SPG","metrics":{"Mean IoU":"68.4","Number of params":"0.290M","Params (M)":"0.29","mAcc":"78.3","oAcc":"87.9"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/point-cloud-oversegmentation-with-graph","paper_url":"http://arxiv.org/abs/1904.02113v1","paper_title":"Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning","code":"https://github.com/loicland/superpoint_graph","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":12,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"FKAConv","metrics":{"Mean IoU":"68.4","Number of params":"N/A"},"uses_additional_data":false,"paper_date":"2020-04-09","paper":"/paper/lightconvpoint-convolution-for-points","paper_url":"https://arxiv.org/abs/2004.04462v3","paper_title":"FKAConv: Feature-Kernel Alignment for Point Cloud Convolution","code":"https://github.com/valeoai/FKAConv","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"ConvPoint","metrics":{"Mean IoU":"68.2","Number of params":"4.7M","Params (M)":"4.1","oAcc":"88.8"},"uses_additional_data":false,"paper_date":"2019-04-04","paper":"/paper/generalizing-discrete-convolutions-for","paper_url":"https://arxiv.org/abs/1904.02375v5","paper_title":"ConvPoint: Continuous Convolutions for Point Cloud Processing","code":"https://github.com/aboulch/ConvPoint","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":31,"model":"JSENet","metrics":{"Mean IoU":"67.7","Number of params":"N/A"},"uses_additional_data":false,"paper_date":"2020-07-14","paper":"/paper/jsenet-joint-semantic-segmentation-and-edge","paper_url":"https://arxiv.org/abs/2007.06888v1","paper_title":"JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds","code":"https://github.com/hzykent/JSENet","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"CT2","metrics":{"Mean IoU":"67.4","Number of params":"N/A"},"uses_additional_data":false,"paper_date":"2020-07-22","paper":"/paper/cloud-transformers","paper_url":"https://arxiv.org/abs/2007.11679v4","paper_title":"Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":33,"model":"ShellNet","metrics":{"Mean IoU":"66.8","Number of params":"N/A"},"uses_additional_data":false,"paper_date":"2019-08-17","paper":"/paper/shellnet-efficient-point-cloud-convolutional","paper_url":"https://arxiv.org/abs/1908.06295v1","paper_title":"ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics","code":"https://github.com/hkust-vgd/shellnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"PointWeb","metrics":{"Mean IoU":"66.7","Number of params":"N/A","mAcc":"76.2","oAcc":"87.3"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/pointweb-enhancing-local-neighborhood","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Zhao_PointWeb_Enhancing_Local_Neighborhood_Features_for_Point_Cloud_Processing_CVPR_2019_paper.html","paper_title":"PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing","code":"https://github.com/hszhao/PointWeb","n_code_links":1,"syntology":null},{"rank_in_archive_order":35,"model":"PointCNN","metrics":{"Mean IoU":"65.4","Number of params":"N/A","oAcc":"88.1"},"uses_additional_data":false,"paper_date":"2019-04-16","paper":"/paper/190408017","paper_url":"http://arxiv.org/abs/1904.08017v1","paper_title":"A-CNN: Annularly Convolutional Neural Networks on Point Clouds","code":"https://github.com/artemkomarichev/a-cnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"PointCNN","metrics":{"Mean IoU":"65.4","Number of params":"N/A"},"uses_additional_data":false,"paper_date":"2020-12-16","paper":"/paper/point-transformer-1","paper_url":"https://arxiv.org/abs/2012.09164v2","paper_title":"Point Transformer","code":"https://github.com/Pointcept/Pointcept","n_code_links":24,"syntology":null},{"rank_in_archive_order":37,"model":"MinkowskiNet","metrics":{"Mean IoU":"65.4","Number of params":"37.9M","Params (M)":"37.9"},"uses_additional_data":false,"paper_date":"2019-04-18","paper":"/paper/4d-spatio-temporal-convnets-minkowski","paper_url":"https://arxiv.org/abs/1904.08755v4","paper_title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","code":"https://github.com/NVIDIA/MinkowskiEngine","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":38,"model":"DSPoint","metrics":{"Mean IoU":"63.3","Number of params":"N/A","mAcc":"70.9"},"uses_additional_data":false,"paper_date":"2021-11-19","paper":"/paper/dspoint-dual-scale-point-cloud-recognition","paper_url":"https://arxiv.org/abs/2111.10332v4","paper_title":"DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion","code":"https://github.com/adonis-galaxy/dspoint","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"A-CNN","metrics":{"Mean IoU":"62.9","Number of params":"N/A","oAcc":"87.3"},"uses_additional_data":false,"paper_date":"2019-04-16","paper":"/paper/190408017","paper_url":"http://arxiv.org/abs/1904.08017v1","paper_title":"A-CNN: Annularly Convolutional Neural Networks on Point Clouds","code":"https://github.com/artemkomarichev/a-cnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"SPG","metrics":{"Mean IoU":"62.1","Number of params":"0.290M","Params (M)":"0.29","mAcc":"73","oAcc":"85.5"},"uses_additional_data":false,"paper_date":"2017-11-27","paper":"/paper/large-scale-point-cloud-semantic-segmentation","paper_url":"http://arxiv.org/abs/1711.09869v2","paper_title":"Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs","code":"https://github.com/loicland/superpoint_graph","n_code_links":2,"syntology":null},{"rank_in_archive_order":41,"model":"SPGraph","metrics":{"Mean IoU":"62.1","Number of params":"N/A","oAcc":"85.5"},"uses_additional_data":false,"paper_date":"2019-04-16","paper":"/paper/190408017","paper_url":"http://arxiv.org/abs/1904.08017v1","paper_title":"A-CNN: Annularly Convolutional Neural Networks on Point Clouds","code":"https://github.com/artemkomarichev/a-cnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"SPGraph","metrics":{"Mean IoU":"62.1","Number of params":"N/A"},"uses_additional_data":false,"paper_date":"2020-12-16","paper":"/paper/point-transformer-1","paper_url":"https://arxiv.org/abs/2012.09164v2","paper_title":"Point Transformer","code":"https://github.com/Pointcept/Pointcept","n_code_links":24,"syntology":null},{"rank_in_archive_order":43,"model":"JSNet","metrics":{"Mean IoU":"61.7","Number of params":"N/A","mAcc":"71.7","oAcc":"88.7"},"uses_additional_data":false,"paper_date":"2019-12-20","paper":"/paper/191209654","paper_url":"https://arxiv.org/abs/1912.09654v1","paper_title":"JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds","code":"https://github.com/dlinzhao/JSNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":44,"model":"DeepGCN","metrics":{"Mean IoU":"60.0","Number of params":"N/A","oAcc":"85.9"},"uses_additional_data":false,"paper_date":"2019-10-15","paper":"/paper/deepgcns-making-gcns-go-as-deep-as-cnns","paper_url":"https://arxiv.org/abs/1910.06849v3","paper_title":"DeepGCNs: Making GCNs Go as Deep as CNNs","code":"https://github.com/lightaime/deep_gcns_torch/tree/master/examples/ogb","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":8,"n_samples":9,"n_pointer_only_licence":1}},{"rank_in_archive_order":45,"model":"ASIS","metrics":{"Mean IoU":"59.3","Number of params":"N/A"},"uses_additional_data":false,"paper_date":"2019-02-26","paper":"/paper/associatively-segmenting-instances-and","paper_url":"http://arxiv.org/abs/1902.09852v2","paper_title":"Associatively Segmenting Instances and Semantics in Point Clouds","code":"https://github.com/WXinlong/ASIS","n_code_links":3,"syntology":null},{"rank_in_archive_order":46,"model":"RSNet","metrics":{"Mean IoU":"56.5","Number of params":"N/A","mAcc":"66.5"},"uses_additional_data":false,"paper_date":"2018-02-13","paper":"/paper/recurrent-slice-networks-for-3d-segmentation","paper_url":"http://arxiv.org/abs/1802.04402v2","paper_title":"Recurrent Slice Networks for 3D Segmentation of Point Clouds","code":"https://github.com/qianguih/RSNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":47,"model":"3P-RNN","metrics":{"Mean IoU":"56.3","Number of params":"N/A","oAcc":"86.9"},"uses_additional_data":false,"paper_date":"2019-04-16","paper":"/paper/190408017","paper_url":"http://arxiv.org/abs/1904.08017v1","paper_title":"A-CNN: Annularly Convolutional Neural Networks on Point Clouds","code":"https://github.com/artemkomarichev/a-cnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":48,"model":"Point-PlaneNet","metrics":{"Mean IoU":"54.8","Number of params":"N/A","oAcc":"83.9"},"uses_additional_data":false,"paper_date":"2020-05-01","paper":"/paper/point-planenet-plane-kernel-based","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S1051200419301873","paper_title":"Point-PlaneNet: Plane kernel based convolutional neural network for point clouds analysis","code":"https://github.com/moeinp70/Point-Planenet","n_code_links":1,"syntology":null},{"rank_in_archive_order":49,"model":"SMS","metrics":{"Mean IoU":"51.74","Number of params":"N/A"},"uses_additional_data":false,"paper_date":"2021-09-01","paper":"/paper/point-cloud-pre-training-by-mixing-and","paper_url":"https://arxiv.org/abs/2109.00452v3","paper_title":"Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes","code":"https://github.com/cyysc1998/3D-Pretraining","n_code_links":1,"syntology":null},{"rank_in_archive_order":50,"model":"PointNet","metrics":{"Mean IoU":"47.6","Number of params":"N/A","oAcc":"78.5"},"uses_additional_data":false,"paper_date":"2019-04-16","paper":"/paper/190408017","paper_url":"http://arxiv.org/abs/1904.08017v1","paper_title":"A-CNN: Annularly Convolutional Neural Networks on Point Clouds","code":"https://github.com/artemkomarichev/a-cnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":51,"model":"PointNet","metrics":{"Mean IoU":"47.6","Number of params":"N/A"},"uses_additional_data":false,"paper_date":"2020-12-16","paper":"/paper/point-transformer-1","paper_url":"https://arxiv.org/abs/2012.09164v2","paper_title":"Point Transformer","code":"https://github.com/Pointcept/Pointcept","n_code_links":24,"syntology":null},{"rank_in_archive_order":52,"model":"RandLA-Net","metrics":{"Number of params":"1.2M","Params (M)":"1.2","mAcc":"81.5","mIoU":"68.5","oAcc":"87.1"},"uses_additional_data":false,"paper_date":"2019-11-25","paper":"/paper/191111236","paper_url":"https://arxiv.org/abs/1911.11236v3","paper_title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds","code":"https://github.com/intel-isl/Open3D-ML","n_code_links":9,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":53,"model":"PointNet","metrics":{"Number of params":"N/A","mAcc":"66.2"},"uses_additional_data":false,"paper_date":"2016-12-02","paper":"/paper/pointnet-deep-learning-on-point-sets-for-3d","paper_url":"http://arxiv.org/abs/1612.00593v2","paper_title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","code":"https://github.com/charlesq34/pointnet","n_code_links":110,"syntology":{"n_ran":89,"n_unverified":75,"n_samples":164,"n_pointer_only_licence":90}},{"rank_in_archive_order":54,"model":"BIM-Net","metrics":{"mIoU":"59.5"},"uses_additional_data":false,"paper_date":"2023-09-11","paper":"/paper/fully-automated-scan-to-bim-via-point-cloud","paper_url":"https://ieeexplore.ieee.org/document/10222064","paper_title":"Fully Automated Scan-to-BIM Via Point Cloud Instance Segmentation","code":"https://github.com/LTTM/Scan-to-BIM","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":18,"rows_with_any_sample_ran":16,"distinct_papers_with_graph_line":17,"distinct_papers_with_any_sample_ran":15,"samples_over_distinct_papers":{"n_ran":129,"n_unverified":175,"n_samples":304,"n_pointer_only_licence":100,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":136,"n_unverified":185,"n_samples":321,"n_pointer_only_licence":100,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}