{"url":"/sota/4d-panoptic-segmentation-on-semantickitti","task":{"name":"4D Panoptic Segmentation","url":"/task/4d-panoptic-segmentation","note":null},"dataset":{"name":"SemanticKITTI","url":"/dataset/semantickitti"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**4D Panoptic Segmentation** is a computer vision task that extends [video panoptic segmentation](https://paperswithcode.com/task/video-panoptic-segmentation) to point cloud sequences. That is, given a point cloud sequence, the goal is to predict the semantic class of each point while consistently tracking object instances. Here, the points belonging to the same object instance should be assigned the same instance ID throughout the point cloud sequence. [LSTQ metric](https://arxiv.org/pdf/2102.12472.pdf) is used to evaluate the performance of this task. Video credit:    [Mask4Former](https://yilmazkadir.github.io/Mask4Former/)","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":["LSTQ"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"LSTQ":null}},"counts":{"rows":7,"rows_with_code":6,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Mask4Former","metrics":{"LSTQ":"68.4"},"uses_additional_data":false,"paper_date":"2023-09-28","paper":"/paper/mask4d-mask-transformer-for-4d-panoptic","paper_url":"https://arxiv.org/abs/2309.16133v2","paper_title":"Mask4Former: Mask Transformer for 4D Panoptic Segmentation","code":"https://github.com/YilmazKadir/Mask4Former","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Eq-4D-StOP","metrics":{"LSTQ":"67.8"},"uses_additional_data":false,"paper_date":"2023-03-28","paper":"/paper/4d-panoptic-segmentation-as-invariant-and","paper_url":"https://arxiv.org/abs/2303.15651v2","paper_title":"4D Panoptic Segmentation as Invariant and Equivariant Field Prediction","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Mask4D","metrics":{"LSTQ":"64.3"},"uses_additional_data":false,"paper_date":"2023-09-18","paper":"/paper/mask4d-end-to-end-mask-based-4d-panoptic","paper_url":"https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/marcuzzi2023ral-meem.pdf","paper_title":"Mask4D: End-to-End Mask-Based 4D Panoptic Segmentation for LiDAR Sequences","code":"https://github.com/PRBonn/Mask4D","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"4D-StOP","metrics":{"LSTQ":"63.9"},"uses_additional_data":false,"paper_date":"2022-09-29","paper":"/paper/4d-stop-panoptic-segmentation-of-4d-lidar","paper_url":"https://arxiv.org/abs/2209.14858v1","paper_title":"4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregation","code":"https://github.com/larskreuzberg/4d-stop","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":5,"model":"CIA","metrics":{"LSTQ":"63.1"},"uses_additional_data":false,"paper_date":"2021-12-01","paper":"/paper/contrastive-instance-association-for-4d","paper_url":"https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/marcuzzi2022ral.pdf","paper_title":"Contrastive Instance Association for 4D Panoptic Segmentation using Sequences of 3D LiDAR Scans","code":"https://github.com/prbonn/contrastive_association","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"4D-DS-Net","metrics":{"LSTQ":"62.3"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/lidar-based-4d-panoptic-segmentation-via","paper_url":"https://arxiv.org/abs/2203.07186v1","paper_title":"LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Network","code":"https://github.com/hongfz16/DS-Net","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":7,"model":"4D-PLS","metrics":{"LSTQ":"56.9"},"uses_additional_data":false,"paper_date":"2021-02-24","paper":"/paper/4d-panoptic-lidar-segmentation","paper_url":"https://arxiv.org/abs/2102.12472v2","paper_title":"4D Panoptic LiDAR Segmentation","code":"https://github.com/mehmetaygun/4d-pls","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":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5,"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"}}}