{"url":"/sota/3d-part-segmentation-on-shapenet-part","task":{"name":"3D Part Segmentation","url":"/task/3d-part-segmentation","note":null},"dataset":{"name":"ShapeNet-Part","url":"/dataset/shapenet"},"category":"Computer Vision","categories":["Computer Code","Computer Vision","Medical","Robots"],"category_note":null,"description":"Segmenting 3D object parts\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [MeshCNN: A Network with an Edge](https://arxiv.org/pdf/1809.05910v2.pdf) )</span>","description_from":"task","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":["Instance Average IoU","Class Average IoU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Instance Average IoU":"higher","Class Average IoU":"higher"}},"counts":{"rows":67,"rows_with_code":54,"rows_with_paper_page":65,"rows_dated":66,"rows_using_additional_data":5},"rows":[{"rank_in_archive_order":1,"model":"GeomGCNN","metrics":{"Instance Average IoU":"89.1"},"uses_additional_data":false,"paper_date":"2021-03-28","paper":"/paper/exploiting-local-geometry-for-feature-and","paper_url":"https://arxiv.org/abs/2103.15226v1","paper_title":"Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Ours","metrics":{"Instance Average IoU":"88.1"},"uses_additional_data":false,"paper_date":"2024-11-01","paper":"/paper/beyond-local-patches-preserving-global-local","paper_url":"https://www.sciencedirect.com/science/article/pii/S0031320324004631","paper_title":"Beyond local patches: Preserving global–local interactions by enhancing self-attention via 3D point cloud tokenization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"AVS-Net","metrics":{"Class Average IoU":"85.7","Instance Average IoU":"87.3"},"uses_additional_data":false,"paper_date":"2024-02-27","paper":"/paper/avs-net-point-sampling-with-adaptive-voxel","paper_url":"https://arxiv.org/abs/2402.17521v3","paper_title":"AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understanding","code":"https://github.com/yhc2021/avs-net","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"SPoTr","metrics":{"Class Average IoU":"85.4","Instance Average IoU":"87.2"},"uses_additional_data":false,"paper_date":"2023-03-29","paper":"/paper/self-positioning-point-based-transformer-for","paper_url":"https://arxiv.org/abs/2303.16450v1","paper_title":"Self-positioning Point-based Transformer for Point Cloud Understanding","code":"https://github.com/mlvlab/spotr","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"PointNeXt","metrics":{"Class Average IoU":"85.2","Instance Average IoU":"87.1"},"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":10,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"Diffusion Unit","metrics":{"Class Average IoU":"85.2","Instance Average IoU":"87.1"},"uses_additional_data":false,"paper_date":"2022-09-20","paper":"/paper/interpretable-edge-enhancement-and","paper_url":"https://arxiv.org/abs/2209.09483v3","paper_title":"Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentation","code":"https://github.com/martianxiu/diffusionunit","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"CurveNet+GAM","metrics":{"Instance Average IoU":"87.0"},"uses_additional_data":false,"paper_date":"2015-12-14","paper":null,"paper_url":"http://arxiv.org/abs/1505.07110v2","paper_title":"$(0, 4)$ dualities","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"AGCN","metrics":{"Class Average IoU":"85.7","Instance Average IoU":"86.9"},"uses_additional_data":false,"paper_date":"2021-11-25","paper":"/paper/agcn-adversarial-graph-convolutional-network","paper_url":"https://www.bmvc2021-virtualconference.com/assets/papers/1545.pdf","paper_title":"AGCN: Adversarial Graph Convolutional Network for 3D Point Cloud Segmentation","code":"https://github.com/edshkim98/GAGCN","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"PointMLP+TAP","metrics":{"Class Average IoU":"85.2","Instance Average IoU":"86.9"},"uses_additional_data":false,"paper_date":"2023-07-27","paper":"/paper/take-a-photo-3d-to-2d-generative-pre-training","paper_url":"https://arxiv.org/abs/2307.14971v2","paper_title":"Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models","code":"https://github.com/wangzy22/tap","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"DeltaConv (U-ResNet)","metrics":{"Instance Average IoU":"86.9"},"uses_additional_data":false,"paper_date":"2021-11-16","paper":"/paper/deltaconv-anisotropic-point-cloud-learning","paper_url":"https://arxiv.org/abs/2111.08799v5","paper_title":"DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds","code":"https://github.com/rubenwiersma/deltaconv","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"PointVector-S(C=64)","metrics":{"Instance Average IoU":"86.9"},"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":10,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"OTMae3D","metrics":{"Class Average IoU":"85.1","Instance Average IoU":"86.8"},"uses_additional_data":true,"paper_date":"2024-12-26","paper":"/paper/rethinking-masked-representation-learning-for","paper_url":"https://ieeexplore.ieee.org/document/10815033","paper_title":"Rethinking Masked Representation Learning for 3D Point Cloud Understanding","code":"https://github.com/OpenSpaceAI/OTMae3D","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Spherical Kernel","metrics":{"Class Average IoU":"84.9","Instance Average IoU":"86.8"},"uses_additional_data":false,"paper_date":"2019-09-20","paper":"/paper/spherical-kernel-for-efficient-graph","paper_url":"https://arxiv.org/abs/1909.09287v2","paper_title":"Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds","code":"https://github.com/hlei-ziyan/SPH3D-GCN","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":9,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"Ps-CNN","metrics":{"Class Average IoU":"83.4","Instance Average IoU":"86.8"},"uses_additional_data":false,"paper_date":"2019-02-28","paper":"/paper/octree-guided-cnn-with-spherical-kernels-for","paper_url":"http://arxiv.org/abs/1903.00343v1","paper_title":"Octree guided CNN with Spherical Kernels for 3D Point Clouds","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"CurveNet","metrics":{"Instance Average IoU":"86.8"},"uses_additional_data":false,"paper_date":"2021-05-04","paper":"/paper/walk-in-the-cloud-learning-curves-for-point","paper_url":"https://arxiv.org/abs/2105.01288v2","paper_title":"Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis","code":"https://github.com/vinits5/learning3d","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":16,"model":"MKConv","metrics":{"Instance Average IoU":"86.7"},"uses_additional_data":false,"paper_date":"2021-07-27","paper":"/paper/ckconv-learning-feature-voxelization-for","paper_url":"https://arxiv.org/abs/2107.12655v3","paper_title":"MKConv: Multidimensional Feature Representation for Point Cloud Analysis","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"Feature Geometric Net (FG-Net)","metrics":{"Class Average IoU":"87.7","Instance Average IoU":"86.6"},"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":18,"model":"PointGPT","metrics":{"Class Average IoU":"84.8","Instance Average IoU":"86.6"},"uses_additional_data":true,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"PointTransformer","metrics":{"Class Average IoU":"83.7","Instance Average IoU":"86.6"},"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":20,"model":"DeltaNet","metrics":{"Instance Average IoU":"86.6"},"uses_additional_data":false,"paper_date":"2021-11-16","paper":"/paper/deltaconv-anisotropic-point-cloud-learning","paper_url":"https://arxiv.org/abs/2111.08799v5","paper_title":"DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds","code":"https://github.com/rubenwiersma/deltaconv","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"GDANet","metrics":{"Class Average IoU":"85.0","Instance Average IoU":"86.5"},"uses_additional_data":false,"paper_date":"2020-12-20","paper":"/paper/learning-geometry-disentangled-representation","paper_url":"https://arxiv.org/abs/2012.10921v3","paper_title":"Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud","code":"https://github.com/mutianxu/GDANet","n_code_links":3,"syntology":null},{"rank_in_archive_order":22,"model":"ODFNet","metrics":{"Class Average IoU":"83.3","Instance Average IoU":"86.5"},"uses_additional_data":false,"paper_date":"2020-12-08","paper":"/paper/odfnet-using-orientation-distribution","paper_url":"https://arxiv.org/abs/2012.04708v2","paper_title":"ODFNet: Using orientation distribution functions to characterize 3D point clouds","code":"https://github.com/ituvisionlab/ODFNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"Point Voxel Transformer","metrics":{"Instance Average IoU":"86.5"},"uses_additional_data":false,"paper_date":"2021-08-13","paper":"/paper/point-voxel-transformer-an-efficient-approach","paper_url":"https://arxiv.org/abs/2108.06076v4","paper_title":"PVT: Point-Voxel Transformer for Point Cloud Learning","code":"https://github.com/HaochengWan/PVT","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"P2P","metrics":{"Instance Average IoU":"86.5"},"uses_additional_data":false,"paper_date":"2022-08-04","paper":"/paper/p2p-tuning-pre-trained-image-models-for-point","paper_url":"https://arxiv.org/abs/2208.02812v2","paper_title":"P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting","code":"https://github.com/wangzy22/P2P","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"KPConv","metrics":{"Class Average IoU":"85.1","Instance Average IoU":"86.4"},"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":8,"n_unverified":4,"n_samples":12,"n_pointer_only_licence":3}},{"rank_in_archive_order":26,"model":"DensePoint","metrics":{"Class Average IoU":"84.2","Instance Average IoU":"86.4"},"uses_additional_data":false,"paper_date":"2019-09-09","paper":"/paper/densepoint-learning-densely-contextual","paper_url":"https://arxiv.org/abs/1909.03669v1","paper_title":"DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing","code":"https://github.com/Yochengliu/DensePoint","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"DRNet","metrics":{"Class Average IoU":"83.7","Instance Average IoU":"86.4"},"uses_additional_data":false,"paper_date":"2020-05-14","paper":"/paper/dense-resolution-network-for-point-cloud","paper_url":"https://arxiv.org/abs/2005.06734v2","paper_title":"Dense-Resolution Network for Point Cloud Classification and Segmentation","code":"https://github.com/ShiQiu0419/DRNet","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":"PointGrid","metrics":{"Class Average IoU":"82.2","Instance Average IoU":"86.4"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/pointgrid-a-deep-network-for-3d-shape","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Le_PointGrid_A_Deep_CVPR_2018_paper.html","paper_title":"PointGrid: A Deep Network for 3D Shape Understanding","code":"https://github.com/trucleduc/PointGrid","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"Point Cloud Transformer","metrics":{"Instance Average IoU":"86.4"},"uses_additional_data":false,"paper_date":"2020-12-17","paper":"/paper/pct-point-cloud-transformer","paper_url":"https://arxiv.org/abs/2012.09688v4","paper_title":"PCT: Point cloud transformer","code":"https://github.com/qq456cvb/Point-Transformers","n_code_links":11,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"point2vec","metrics":{"Class Average IoU":"84.6","Instance Average IoU":"86.3"},"uses_additional_data":true,"paper_date":"2023-03-29","paper":"/paper/point2vec-for-self-supervised-representation","paper_url":"https://arxiv.org/abs/2303.16570v2","paper_title":"Point2Vec for Self-Supervised Representation Learning on Point Clouds","code":"https://github.com/kabouzeid/point2vec","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"InterpCNN","metrics":{"Class Average IoU":"84.0","Instance Average IoU":"86.3"},"uses_additional_data":false,"paper_date":"2019-08-13","paper":"/paper/interpolated-convolutional-networks-for-3d","paper_url":"https://arxiv.org/abs/1908.04512v1","paper_title":"Interpolated Convolutional Networks for 3D Point Cloud Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":32,"model":"PVCNN volumetric","metrics":{"Instance Average IoU":"86.2"},"uses_additional_data":false,"paper_date":"2019-07-08","paper":"/paper/point-voxel-cnn-for-efficient-3d-deep","paper_url":"https://arxiv.org/abs/1907.03739v2","paper_title":"Point-Voxel CNN for Efficient 3D Deep Learning","code":"https://github.com/isl-org/Open3D-ML","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":5}},{"rank_in_archive_order":33,"model":"RS-CNN","metrics":{"Instance Average IoU":"86.2"},"uses_additional_data":false,"paper_date":"2019-04-16","paper":"/paper/relation-shape-convolutional-neural-network","paper_url":"https://arxiv.org/abs/1904.07601v3","paper_title":"Relation-Shape Convolutional Neural Network for Point Cloud Analysis","code":"https://github.com/Yochengliu/Relation-Shape-CNN","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":34,"model":"Ours","metrics":{"Instance Average IoU":"86.2"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/exploiting-inductive-bias-in-transformer-for","paper_url":"https://arxiv.org/abs/2304.14124v1","paper_title":"Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation","code":"https://github.com/jiamang/ibt","n_code_links":1,"syntology":null},{"rank_in_archive_order":35,"model":"PointCNN","metrics":{"Class Average IoU":"84.6","Instance Average IoU":"86.14"},"uses_additional_data":false,"paper_date":"2018-01-23","paper":"/paper/pointcnn-convolution-on-mathcalx-transformed","paper_url":"http://arxiv.org/abs/1801.07791v5","paper_title":"PointCNN: Convolution On $\\mathcal{X}$-Transformed Points","code":"https://github.com/pyg-team/pytorch_geometric","n_code_links":16,"syntology":null},{"rank_in_archive_order":36,"model":"ASSANet","metrics":{"Instance Average IoU":"86.1"},"uses_additional_data":false,"paper_date":"2021-10-20","paper":"/paper/anisotropic-separable-set-abstraction-for","paper_url":"https://arxiv.org/abs/2110.10538v2","paper_title":"ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning","code":"https://github.com/guochengqian/assanet","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":10,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":37,"model":"SSCN","metrics":{"Instance Average IoU":"86.0"},"uses_additional_data":false,"paper_date":"2017-06-05","paper":"/paper/submanifold-sparse-convolutional-networks","paper_url":"http://arxiv.org/abs/1706.01307v1","paper_title":"Submanifold Sparse Convolutional Networks","code":"https://github.com/facebookresearch/SparseConvNet","n_code_links":8,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":38,"model":"Point Transformer","metrics":{"Instance Average IoU":"85.9"},"uses_additional_data":false,"paper_date":"2020-11-02","paper":"/paper/point-transformer","paper_url":"https://arxiv.org/abs/2011.00931v2","paper_title":"Point Transformer","code":"https://github.com/qq456cvb/Point-Transformers","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":39,"model":"DSPoint","metrics":{"Class Average IoU":"83.9","Instance Average IoU":"85.8"},"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":40,"model":"APES (global_based downsample)","metrics":{"Class Average IoU":"83.7","Instance Average IoU":"85.8"},"uses_additional_data":false,"paper_date":"2023-02-28","paper":"/paper/attention-based-point-cloud-edge-sampling","paper_url":"https://arxiv.org/abs/2302.14673v2","paper_title":"Attention-based Point Cloud Edge Sampling","code":"https://github.com/JunweiZheng93/APES","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":41,"model":"ConvPoint","metrics":{"Class Average IoU":"83.4","Instance Average IoU":"85.8"},"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":42,"model":"SGPN","metrics":{"Instance Average IoU":"85.8"},"uses_additional_data":false,"paper_date":"2017-11-23","paper":"/paper/sgpn-similarity-group-proposal-network-for-3d","paper_url":"https://arxiv.org/abs/1711.08588v2","paper_title":"SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation","code":"https://github.com/laughtervv/SGPN","n_code_links":1,"syntology":null},{"rank_in_archive_order":43,"model":"PointConv","metrics":{"Class Average IoU":"82.8","Instance Average IoU":"85.7"},"uses_additional_data":false,"paper_date":"2018-11-17","paper":"/paper/pointconv-deep-convolutional-networks-on-3d","paper_url":"https://arxiv.org/abs/1811.07246v3","paper_title":"PointConv: Deep Convolutional Networks on 3D Point Clouds","code":"https://github.com/vinits5/learning3d","n_code_links":9,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":1}},{"rank_in_archive_order":44,"model":"PointNet++ + SageMix","metrics":{"Instance Average IoU":"85.7"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/sagemix-saliency-guided-mixup-for-point","paper_url":"https://arxiv.org/abs/2210.06944v1","paper_title":"SageMix: Saliency-Guided Mixup for Point Clouds","code":"https://github.com/mlvlab/SageMix","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":45,"model":"APES (local_based downsample)","metrics":{"Class Average IoU":"83.1","Instance Average IoU":"85.6"},"uses_additional_data":false,"paper_date":"2023-02-28","paper":"/paper/attention-based-point-cloud-edge-sampling","paper_url":"https://arxiv.org/abs/2302.14673v2","paper_title":"Attention-based Point Cloud Edge Sampling","code":"https://github.com/JunweiZheng93/APES","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":46,"model":"DGCNN + MD","metrics":{"Instance Average IoU":"85.5"},"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":47,"model":"SFCNN","metrics":{"Class Average IoU":"82.7","Instance Average IoU":"85.4"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/spherical-fractal-convolutional-neural","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Rao_Spherical_Fractal_Convolutional_Neural_Networks_for_Point_Cloud_Recognition_CVPR_2019_paper.html","paper_title":"Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":48,"model":"DGCNN + SageMix","metrics":{"Instance Average IoU":"85.4"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/sagemix-saliency-guided-mixup-for-point","paper_url":"https://arxiv.org/abs/2210.06944v1","paper_title":"SageMix: Saliency-Guided Mixup for Point Clouds","code":"https://github.com/mlvlab/SageMix","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":49,"model":"SpiderCNN","metrics":{"Class Average IoU":"82.4","Instance Average IoU":"85.3"},"uses_additional_data":false,"paper_date":"2018-03-30","paper":"/paper/spidercnn-deep-learning-on-point-sets-with","paper_url":"http://arxiv.org/abs/1803.11527v3","paper_title":"SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters","code":"https://github.com/xyf513/SpiderCNN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"SRN","metrics":{"Class Average IoU":"82.2","Instance Average IoU":"85.3"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/structural-relational-reasoning-of-point","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Duan_Structural_Relational_Reasoning_of_Point_Clouds_CVPR_2019_paper.html","paper_title":"Structural Relational Reasoning of Point Clouds","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":51,"model":"DGCNN","metrics":{"Instance Average IoU":"85.2"},"uses_additional_data":false,"paper_date":"2018-01-24","paper":"/paper/dynamic-graph-cnn-for-learning-on-point","paper_url":"https://arxiv.org/abs/1801.07829v2","paper_title":"Dynamic Graph CNN for Learning on Point Clouds","code":"https://github.com/WangYueFt/dgcnn","n_code_links":21,"syntology":{"n_ran":16,"n_unverified":28,"n_samples":44,"n_pointer_only_licence":31}},{"rank_in_archive_order":52,"model":"P2Sequence","metrics":{"Instance Average IoU":"85.2"},"uses_additional_data":false,"paper_date":"2018-11-06","paper":"/paper/point2sequence-learning-the-shape","paper_url":"http://arxiv.org/abs/1811.02565v2","paper_title":"Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":53,"model":"Point-PlaneNet","metrics":{"Class Average IoU":"82.5","Instance Average IoU":"85.1"},"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":54,"model":"3D-GCN","metrics":{"Class Average IoU":"82.1","Instance Average IoU":"85.1"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/convolution-in-the-cloud-learning-deformable","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Lin_Convolution_in_the_Cloud_Learning_Deformable_Kernels_in_3D_Graph_CVPR_2020_paper.html","paper_title":"Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis","code":"https://github.com/j1a0m0e4sNTU/3dgcn","n_code_links":1,"syntology":null},{"rank_in_archive_order":55,"model":"PointNet++","metrics":{"Class Average IoU":"81.9","Instance Average IoU":"85.1"},"uses_additional_data":false,"paper_date":"2017-06-07","paper":"/paper/pointnet-deep-hierarchical-feature-learning","paper_url":"http://arxiv.org/abs/1706.02413v1","paper_title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","code":"https://github.com/yanx27/Pointnet_Pointnet2_pytorch","n_code_links":68,"syntology":{"n_ran":36,"n_unverified":31,"n_samples":67,"n_pointer_only_licence":26}},{"rank_in_archive_order":56,"model":"3D-JEPA","metrics":{"Class Average IoU":"86.41","Instance Average IoU":"84.93"},"uses_additional_data":true,"paper_date":"2024-09-24","paper":"/paper/3d-jepa-a-joint-embedding-predictive","paper_url":"https://arxiv.org/abs/2409.15803v1","paper_title":"3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":57,"model":"SO-Net","metrics":{"Instance Average IoU":"84.9"},"uses_additional_data":false,"paper_date":"2018-03-12","paper":"/paper/so-net-self-organizing-network-for-point","paper_url":"http://arxiv.org/abs/1803.04249v4","paper_title":"SO-Net: Self-Organizing Network for Point Cloud Analysis","code":"https://github.com/lijx10/SO-Net","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":58,"model":"SSCNN","metrics":{"Class Average IoU":"82.0","Instance Average IoU":"84.7"},"uses_additional_data":false,"paper_date":"2016-12-02","paper":"/paper/syncspeccnn-synchronized-spectral-cnn-for-3d","paper_url":"http://arxiv.org/abs/1612.00606v1","paper_title":"SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":59,"model":"SPLATNet 3D","metrics":{"Class Average IoU":"82.0","Instance Average IoU":"84.6"},"uses_additional_data":false,"paper_date":"2018-02-22","paper":"/paper/splatnet-sparse-lattice-networks-for-point","paper_url":"http://arxiv.org/abs/1802.08275v4","paper_title":"SPLATNet: Sparse Lattice Networks for Point Cloud Processing","code":"https://github.com/NVlabs/splatnet","n_code_links":2,"syntology":null},{"rank_in_archive_order":60,"model":"3D-UNet [Cicek:2016un]","metrics":{"Instance Average IoU":"84.6"},"uses_additional_data":false,"paper_date":"2016-06-21","paper":"/paper/3d-u-net-learning-dense-volumetric","paper_url":"http://arxiv.org/abs/1606.06650v1","paper_title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","code":"https://github.com/wolny/pytorch-3dunet","n_code_links":27,"syntology":{"n_ran":55,"n_unverified":21,"n_samples":76,"n_pointer_only_licence":20}},{"rank_in_archive_order":61,"model":"3DmFV-Net","metrics":{"Instance Average IoU":"84.3"},"uses_additional_data":false,"paper_date":"2017-11-22","paper":"/paper/3d-point-cloud-classification-and","paper_url":"http://arxiv.org/abs/1711.08241v1","paper_title":"3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks","code":"https://github.com/sitzikbs/3DmFV-Net","n_code_links":3,"syntology":null},{"rank_in_archive_order":62,"model":"Point-JEPA","metrics":{"Class Average IoU":"85.8","Instance Average IoU":"83.9 "},"uses_additional_data":true,"paper_date":"2024-04-25","paper":"/paper/point-jepa-a-joint-embedding-predictive","paper_url":"https://arxiv.org/abs/2404.16432v5","paper_title":"Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud","code":"https://github.com/Ayumu-J-S/Point-JEPA","n_code_links":1,"syntology":null},{"rank_in_archive_order":63,"model":"PointNet","metrics":{"Instance Average IoU":"83.7"},"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":64,"model":"Kd-net","metrics":{"Class Average IoU":"77.4","Instance Average IoU":"82.3"},"uses_additional_data":false,"paper_date":"2017-04-04","paper":"/paper/escape-from-cells-deep-kd-networks-for-the","paper_url":"http://arxiv.org/abs/1704.01222v2","paper_title":"Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models","code":"https://github.com/fxia22/kdnet.pytorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":65,"model":"AdaCrossNet","metrics":{"Class Average IoU":"85.1"},"uses_additional_data":false,"paper_date":"2025-01-02","paper":"/paper/adacrossnet-adaptive-dynamic-loss-weighting","paper_url":"https://inass.org/wp-content/uploads/2024/10/2025022911-2.pdf","paper_title":"AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud Learning","code":"https://github.com/virgantara/AdaCrossNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":66,"model":"PartNet","metrics":{"Class Average IoU":"84.1"},"uses_additional_data":false,"paper_date":"2019-03-02","paper":"/paper/partnet-a-recursive-part-decomposition","paper_url":"https://arxiv.org/abs/1903.00709v5","paper_title":"PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":67,"model":"PointNet++ (ssg) + JM3D","metrics":{"Class Average IoU":"82.1"},"uses_additional_data":false,"paper_date":"2023-08-06","paper":"/paper/beyond-first-impressions-integrating-joint","paper_url":"https://arxiv.org/abs/2308.02982v2","paper_title":"Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation","code":"https://github.com/mr-neko/jm3d","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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":28,"rows_with_any_sample_ran":26,"distinct_papers_with_graph_line":26,"distinct_papers_with_any_sample_ran":25,"samples_over_distinct_papers":{"n_ran":291,"n_unverified":221,"n_samples":512,"n_pointer_only_licence":188,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":292,"n_unverified":222,"n_samples":514,"n_pointer_only_licence":188,"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"}}}