{"url":"/sota/3d-semantic-segmentation-on-dales","task":{"name":"3D Semantic Segmentation","url":"/task/3d-semantic-segmentation","note":null},"dataset":{"name":"DALES","url":"/dataset/dales"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**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.","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":["mIoU","Overall Accuracy","Model size"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mIoU":null,"Overall Accuracy":"higher","Model size":null}},"counts":{"rows":9,"rows_with_code":9,"rows_with_paper_page":9,"rows_dated":9,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"KPConv","metrics":{"Model size":"14M","Overall Accuracy":"97.8","mIoU":"81.1"},"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":8,"n_unverified":4,"n_samples":12,"n_pointer_only_licence":3}},{"rank_in_archive_order":2,"model":"Superpoint Transformer","metrics":{"Model size":"212K","Overall Accuracy":"97.5","mIoU":"79.6"},"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":3,"model":"EyeNet","metrics":{"mIoU":"79.6"},"uses_additional_data":false,"paper_date":"2023-01-30","paper":"/paper/mrnet-multiple-input-receptive-field-network","paper_url":"https://arxiv.org/abs/2301.12972v3","paper_title":"Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scene","code":"https://github.com/Yacovitch/EyeNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"SuperCluster","metrics":{"Model size":"210M","mIoU":"77.3"},"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":5,"model":"PointNet++","metrics":{"Model size":"3.0M","Overall Accuracy":"95.7","mIoU":"68.3"},"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":6,"model":"ConvPoint","metrics":{"Model size":"4.7M","Overall Accuracy":"97.2","mIoU":"67.4"},"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":7,"model":"SPG","metrics":{"Model size":"280K","Overall Accuracy":"95.5","mIoU":"60.6"},"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":8,"model":"PointCNN","metrics":{"Model size":"N/A","Overall Accuracy":"97.2","mIoU":"58.4"},"uses_additional_data":false,"paper_date":"2018-12-01","paper":"/paper/pointcnn-convolution-on-x-transformed-points","paper_url":"http://papers.nips.cc/paper/7362-pointcnn-convolution-on-x-transformed-points","paper_title":"PointCNN: Convolution On X-Transformed Points","code":"https://github.com/yangyanli/PointCNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"ShellNet","metrics":{"Model size":"N/A","Overall Accuracy":"96.4","mIoU":"57.4"},"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}],"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":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":48,"n_unverified":35,"n_samples":83,"n_pointer_only_licence":33,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":48,"n_unverified":35,"n_samples":83,"n_pointer_only_licence":33,"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"}}}