{"url":"/sota/3d-object-detection-on-sun-rgbd-val","task":{"name":"3D Object Detection","url":"/task/3d-object-detection","note":null},"dataset":{"name":"SUN-RGBD val","url":"/dataset/sun-rgb-d"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**3D Object Detection** is a task in computer vision where the goal is to identify and locate objects in a 3D environment based on their shape, location, and orientation. It involves detecting the presence of objects and determining their location in the 3D space in real-time. This task is crucial for applications such as autonomous vehicles, robotics, and augmented reality.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [AVOD](https://github.com/kujason/avod) )</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":["mAP@0.25","mAP@0.5","Inference Speed (s)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mAP@0.25":"higher","mAP@0.5":"higher","Inference Speed (s)":null}},"counts":{"rows":32,"rows_with_code":21,"rows_with_paper_page":32,"rows_dated":32,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"Point-GCC+TR3D+FF","metrics":{"mAP@0.25":"69.7","mAP@0.5":"54.0"},"uses_additional_data":false,"paper_date":"2023-05-31","paper":"/paper/point-gcc-universal-self-supervised-3d-scene","paper_url":"https://arxiv.org/abs/2305.19623v2","paper_title":"Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast","code":"https://github.com/asterisci/point-gcc","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"TR3D+FF","metrics":{"mAP@0.25":"69.4","mAP@0.5":"53.4"},"uses_additional_data":false,"paper_date":"2023-02-06","paper":"/paper/tr3d-towards-real-time-indoor-3d-object","paper_url":"https://arxiv.org/abs/2302.02858v3","paper_title":"TR3D: Towards Real-Time Indoor 3D Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"DEST (based on V-DETR) (TTA)","metrics":{"mAP@0.25":"69.2","mAP@0.5":"52.2"},"uses_additional_data":false,"paper_date":"2025-03-18","paper":"/paper/state-space-model-meets-transformer-a-new-1","paper_url":"https://arxiv.org/abs/2503.14493v1","paper_title":"State Space Model Meets Transformer: A New Paradigm for 3D Object Detection","code":"https://github.com/OpenSpaceAI/DEST3D","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"V-DETR","metrics":{"mAP@0.25":"68.0","mAP@0.5":"51.1"},"uses_additional_data":false,"paper_date":"2023-08-08","paper":"/paper/v-detr-detr-with-vertex-relative-position","paper_url":"https://arxiv.org/abs/2308.04409v1","paper_title":"V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection","code":"https://github.com/yichaoshen-ms/v-detr","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"Point-GCC+TR3D","metrics":{"mAP@0.25":"67.7","mAP@0.5":"51.0"},"uses_additional_data":false,"paper_date":"2023-05-31","paper":"/paper/point-gcc-universal-self-supervised-3d-scene","paper_url":"https://arxiv.org/abs/2305.19623v2","paper_title":"Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast","code":"https://github.com/asterisci/point-gcc","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"DeMF","metrics":{"mAP@0.25":"67.4","mAP@0.5":"51.2"},"uses_additional_data":false,"paper_date":"2022-07-21","paper":"/paper/boosting-3d-object-detection-via-object","paper_url":"https://arxiv.org/abs/2207.10589v1","paper_title":"Boosting 3D Object Detection via Object-Focused Image Fusion","code":"https://github.com/haoy945/demf","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"TR3D (Geo only)","metrics":{"mAP@0.25":"67.1","mAP@0.5":"50.4"},"uses_additional_data":false,"paper_date":"2023-02-06","paper":"/paper/tr3d-towards-real-time-indoor-3d-object","paper_url":"https://arxiv.org/abs/2302.02858v3","paper_title":"TR3D: Towards Real-Time Indoor 3D Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"CAGroup3D(Geo only)","metrics":{"mAP@0.25":"66.8","mAP@0.5":"50.2"},"uses_additional_data":false,"paper_date":"2022-10-09","paper":"/paper/cagroup3d-class-aware-grouping-for-3d-object","paper_url":"https://arxiv.org/abs/2210.04264v1","paper_title":"CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds","code":"https://github.com/haiyang-w/cagroup3d","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"OctFormer","metrics":{"mAP@0.25":"66.2","mAP@0.5":"50.6"},"uses_additional_data":false,"paper_date":"2023-05-04","paper":"/paper/octformer-octree-based-transformers-for-3d","paper_url":"https://arxiv.org/abs/2305.03045v2","paper_title":"OctFormer: Octree-based Transformers for 3D Point Clouds","code":"https://github.com/Pointcept/Pointcept","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"SPGroup3D(Geo only)","metrics":{"mAP@0.25":"65.4","mAP@0.5":"47.1"},"uses_additional_data":false,"paper_date":"2023-12-21","paper":"/paper/spgroup3d-superpoint-grouping-network-for","paper_url":"https://arxiv.org/abs/2312.13641v1","paper_title":"SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection","code":"https://github.com/zyrant/spgroup3d","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"DEST (based on  GroupFree3D)","metrics":{"mAP@0.25":"65.3","mAP@0.5":"48.4"},"uses_additional_data":false,"paper_date":"2025-03-18","paper":"/paper/state-space-model-meets-transformer-a-new-1","paper_url":"https://arxiv.org/abs/2503.14493v1","paper_title":"State Space Model Meets Transformer: A New Paradigm for 3D Object Detection","code":"https://github.com/OpenSpaceAI/DEST3D","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"TokenFusion","metrics":{"mAP@0.25":"64.9","mAP@0.5":"48.3"},"uses_additional_data":false,"paper_date":"2022-04-19","paper":"/paper/multimodal-token-fusion-for-vision","paper_url":"https://arxiv.org/abs/2204.08721v2","paper_title":"Multimodal Token Fusion for Vision Transformers","code":"https://github.com/huawei-noah/noah-research/tree/master/TokenFusion","n_code_links":11,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":13,"model":"RepSurf-U","metrics":{"mAP@0.25":"64.9","mAP@0.5":"47.7"},"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":13,"n_unverified":2,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"FCAF3D (Geo only)","metrics":{"mAP@0.25":"64.2","mAP@0.5":"48.9"},"uses_additional_data":false,"paper_date":"2021-12-01","paper":"/paper/fcaf3d-fully-convolutional-anchor-free-3d","paper_url":"https://arxiv.org/abs/2112.00322v2","paper_title":"FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection","code":"https://github.com/open-mmlab/mmdetection3d","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"RBGNet(Geo only)","metrics":{"mAP@0.25":"64.1","mAP@0.5":"47.2"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/rbgnet-ray-based-grouping-for-3d-object","paper_url":"https://arxiv.org/abs/2204.02251v1","paper_title":"RBGNet: Ray-based Grouping for 3D Object Detection","code":"https://github.com/haiyang-w/rbgnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"LCPFormer","metrics":{"mAP@0.25":"63.2","mAP@0.5":"46.2"},"uses_additional_data":false,"paper_date":"2022-10-23","paper":"/paper/lcpformer-towards-effective-3d-point-cloud","paper_url":"https://arxiv.org/abs/2210.12755v2","paper_title":"LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers","code":"https://github.com/zhh6425/LocalContextPropagation","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"GroupFree3D(Geo only)","metrics":{"mAP@0.25":"63.0","mAP@0.5":"45.2"},"uses_additional_data":false,"paper_date":"2021-04-01","paper":"/paper/group-free-3d-object-detection-via","paper_url":"https://arxiv.org/abs/2104.00678v2","paper_title":"Group-Free 3D Object Detection via Transformers","code":"https://github.com/zeliu98/Group-Free-3D","n_code_links":4,"syntology":{"n_ran":9,"n_unverified":8,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"HGNet (Geo only)","metrics":{"mAP@0.25":"61.6"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/a-hierarchical-graph-network-for-3d-object","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Chen_A_Hierarchical_Graph_Network_for_3D_Object_Detection_on_Point_CVPR_2020_paper.html","paper_title":"A Hierarchical Graph Network for 3D Object Detection on Point Clouds","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"BRNet(Geo only)","metrics":{"mAP@0.25":"61.1","mAP@0.5":"43.7"},"uses_additional_data":false,"paper_date":"2021-04-13","paper":"/paper/back-tracing-representative-points-for-voting","paper_url":"https://arxiv.org/abs/2104.06114v2","paper_title":"Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds","code":"https://github.com/cheng052/BRNet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"VoteNet (PC-FractalDB)","metrics":{"mAP@0.25":"60.2","mAP@0.5":"35.2"},"uses_additional_data":true,"paper_date":"2022-01-01","paper":"/paper/point-cloud-pre-training-with-natural-3d","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Yamada_Point_Cloud_Pre-Training_With_Natural_3D_Structures_CVPR_2022_paper.html","paper_title":"Point Cloud Pre-Training With Natural 3D Structures","code":"https://github.com/ryosuke-yamada/3dfractaldb","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"H3DNet","metrics":{"mAP@0.25":"60.1","mAP@0.5":"39.0"},"uses_additional_data":false,"paper_date":"2020-06-10","paper":"/paper/h3dnet-3d-object-detection-using-hybrid","paper_url":"https://arxiv.org/abs/2006.05682v3","paper_title":"H3DNet: 3D Object Detection Using Hybrid Geometric Primitives","code":"https://github.com/open-mmlab/mmdetection3d","n_code_links":2,"syntology":null},{"rank_in_archive_order":22,"model":"VoteNet (Geo only)","metrics":{"mAP@0.25":"59.1","mAP@0.5":"35.8"},"uses_additional_data":false,"paper_date":"2019-04-21","paper":"/paper/deep-hough-voting-for-3d-object-detection-in","paper_url":"https://arxiv.org/abs/1904.09664v2","paper_title":"Deep Hough Voting for 3D Object Detection in Point Clouds","code":"https://github.com/open-mmlab/mmdetection3d","n_code_links":13,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":10}},{"rank_in_archive_order":23,"model":"3DETR-m","metrics":{"mAP@0.25":"59.1","mAP@0.5":"32.7"},"uses_additional_data":false,"paper_date":"2021-09-16","paper":"/paper/an-end-to-end-transformer-model-for-3d-object","paper_url":"https://arxiv.org/abs/2109.08141v1","paper_title":"An End-to-End Transformer Model for 3D Object Detection","code":"https://github.com/facebookresearch/3detr","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":24,"model":"COG+surface+context","metrics":{"mAP@0.25":"54.3"},"uses_additional_data":false,"paper_date":"2019-06-11","paper":"/paper/clouds-of-oriented-gradients-for-3d-detection","paper_url":"https://arxiv.org/abs/1906.04725v1","paper_title":"Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene Layouts","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"F-PointNet","metrics":{"Inference Speed (s)":"0.12","mAP@0.25":"54.0"},"uses_additional_data":false,"paper_date":"2017-11-22","paper":"/paper/frustum-pointnets-for-3d-object-detection","paper_url":"http://arxiv.org/abs/1711.08488v2","paper_title":"Frustum PointNets for 3D Object Detection from RGB-D Data","code":"https://github.com/charlesq34/pointnet","n_code_links":68,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":2}},{"rank_in_archive_order":26,"model":"COG+surface","metrics":{"mAP@0.25":"51.0"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/3d-object-detection-with-latent-support","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Ren_3D_Object_Detection_CVPR_2018_paper.html","paper_title":"3D Object Detection With Latent Support Surfaces","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"COG","metrics":{"mAP@0.25":"47.6"},"uses_additional_data":false,"paper_date":"2016-06-01","paper":"/paper/three-dimensional-object-detection-and-layout","paper_url":"http://openaccess.thecvf.com/content_cvpr_2016/html/Ren_Three-Dimensional_Object_Detection_CVPR_2016_paper.html","paper_title":"Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"2D-driven","metrics":{"Inference Speed (s)":"4.15","mAP@0.25":"45.1"},"uses_additional_data":false,"paper_date":"2017-10-01","paper":"/paper/2d-driven-3d-object-detection-in-rgb-d-images","paper_url":"http://openaccess.thecvf.com/content_iccv_2017/html/Lahoud_2D-Driven_3D_Object_ICCV_2017_paper.html","paper_title":"2D-Driven 3D Object Detection in RGB-D Images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"Frustum VoxNet v2 (FPN + 3D ResNetFCN6 V2)","metrics":{"Inference Speed (s)":"0.24","mAP@0.25":"45.0"},"uses_additional_data":false,"paper_date":"2021-02-09","paper":"/paper/3d-object-detection-and-instance-segmentation","paper_url":"https://www.mdpi.com/1424-8220/21/4/1213/htm","paper_title":"3D Object Detection and Instance Segmentation from 3D Range and 2D Color Images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"Frustum VoxNet (+3D ResNetFCN6)","metrics":{"Inference Speed (s)":"0.16","mAP@0.25":"37.7"},"uses_additional_data":false,"paper_date":"2019-10-12","paper":"/paper/frustum-voxnet-for-3d-object-detection-from","paper_url":"https://arxiv.org/abs/1910.05483v3","paper_title":"Frustum VoxNet for 3D object detection from RGB-D or Depth images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":31,"model":"Frustum VoxNet (YOLO v3+3D ResNetFCN6)","metrics":{"Inference Speed (s)":"0.048"},"uses_additional_data":false,"paper_date":"2019-10-12","paper":"/paper/frustum-voxnet-for-3d-object-detection-from","paper_url":"https://arxiv.org/abs/1910.05483v3","paper_title":"Frustum VoxNet for 3D object detection from RGB-D or Depth images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":32,"model":"DSS","metrics":{"Inference Speed (s)":"19.55"},"uses_additional_data":false,"paper_date":"2015-11-07","paper":"/paper/deep-sliding-shapes-for-amodal-3d-object","paper_url":"http://arxiv.org/abs/1511.02300v2","paper_title":"Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images","code":null,"n_code_links":0,"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":11,"rows_with_any_sample_ran":11,"distinct_papers_with_graph_line":10,"distinct_papers_with_any_sample_ran":10,"samples_over_distinct_papers":{"n_ran":59,"n_unverified":31,"n_samples":90,"n_pointer_only_licence":14,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":65,"n_unverified":35,"n_samples":100,"n_pointer_only_licence":14,"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"}}}