{"url":"/task/3d-object-detection","name":"3D Object Detection","slug":"3d-object-detection","description_markdown":"**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>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1576,"papers_with_code":764,"benchmarks":67,"benchmark_tables_in_archive":67,"benchmark_tables_shown":67,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":67,"subtasks":5,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/3d-object-detection-on-nuscenes","slug":"3d-object-detection-on-nuscenes","dataset":"nuScenes","dataset_url":"/dataset/nuscenes","rows_in_archive":372,"metrics":["NDS","mAP","mATE","mASE","mAOE","mAVE","mAAE"],"first_row_in_archive_order":{"model":"EA-LSS","paper_title":"EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detection","paper_url":"/paper/ea-bev-edge-aware-bird-s-eye-view-projector","paper_date":"2023-03-31","arxiv_id":"2303.17895","code_links":[{"title":"hht1996ok/ea-bev","url":"https://github.com/hht1996ok/ea-bev"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-scannetv2","slug":"3d-object-detection-on-scannetv2","dataset":"ScanNetV2","dataset_url":"/dataset/scannet","rows_in_archive":33,"metrics":["mAP@0.5","mAP@0.25"],"first_row_in_archive_order":{"model":"DEST (based on V-DETR) (TTA)","paper_title":"State Space Model Meets Transformer: A New Paradigm for 3D Object Detection","paper_url":"/paper/state-space-model-meets-transformer-a-new-1","paper_date":"2025-03-18","arxiv_id":"2503.14493","code_links":[{"title":"OpenSpaceAI/DEST3D","url":"https://github.com/OpenSpaceAI/DEST3D"}],"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-sun-rgbd-val","slug":"3d-object-detection-on-sun-rgbd-val","dataset":"SUN-RGBD val","dataset_url":"/dataset/sun-rgb-d","rows_in_archive":32,"metrics":["mAP@0.25","mAP@0.5","Inference Speed (s)"],"first_row_in_archive_order":{"model":"Point-GCC+TR3D+FF","paper_title":"Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast","paper_url":"/paper/point-gcc-universal-self-supervised-3d-scene","paper_date":"2023-05-31","arxiv_id":"2305.19623","code_links":[{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-easy","slug":"3d-object-detection-on-kitti-cars-easy","dataset":"KITTI Cars Easy","dataset_url":"/dataset/kitti","rows_in_archive":26,"metrics":["AP"],"first_row_in_archive_order":{"model":"TRTConv","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-hard","slug":"3d-object-detection-on-kitti-cars-hard","dataset":"KITTI Cars Hard","dataset_url":"/dataset/kitti","rows_in_archive":25,"metrics":["AP"],"first_row_in_archive_order":{"model":"TRTConv","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-nuscenes-camera-only","slug":"3d-object-detection-on-nuscenes-camera-only","dataset":"nuScenes Camera Only","dataset_url":"/dataset/nuscenes","rows_in_archive":19,"metrics":["NDS","Future Frame"],"first_row_in_archive_order":{"model":"Far3D","paper_title":"Far3D: Expanding the Horizon for Surround-view 3D Object Detection","paper_url":"/paper/far3d-expanding-the-horizon-for-surround-view","paper_date":"2023-08-18","arxiv_id":"2308.09616","code_links":[{"title":"megvii-research/far3d","url":"https://github.com/megvii-research/far3d"}],"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":8}}},{"leaderboard":"/sota/3d-object-detection-on-kitti-cyclists","slug":"3d-object-detection-on-kitti-cyclists","dataset":"KITTI Cyclists Moderate","dataset_url":"/dataset/kitti","rows_in_archive":13,"metrics":["AP"],"first_row_in_archive_order":{"model":"3D-FCT","paper_title":"3D-FCT: Simultaneous 3D Object Detection and Tracking Using Feature Correlation","paper_url":"/paper/3d-fct-simultaneous-3d-object-detection-and","paper_date":"2021-10-06","arxiv_id":"2110.02531","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-cyclists-easy","slug":"3d-object-detection-on-kitti-cyclists-easy","dataset":"KITTI Cyclists Easy","dataset_url":"/dataset/kitti","rows_in_archive":12,"metrics":["AP"],"first_row_in_archive_order":{"model":"3D-FCT","paper_title":"3D-FCT: Simultaneous 3D Object Detection and Tracking Using Feature Correlation","paper_url":"/paper/3d-fct-simultaneous-3d-object-detection-and","paper_date":"2021-10-06","arxiv_id":"2110.02531","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-cyclists-hard","slug":"3d-object-detection-on-kitti-cyclists-hard","dataset":"KITTI Cyclists Hard","dataset_url":"/dataset/kitti","rows_in_archive":12,"metrics":["AP"],"first_row_in_archive_order":{"model":"SA-Det3D","paper_title":"SA-Det3D: Self-Attention Based Context-Aware 3D Object Detection","paper_url":"/paper/self-attention-based-context-aware-3d-object","paper_date":"2021-01-07","arxiv_id":"2101.02672","code_links":[{"title":"AutoVision-cloud/SA-Det3D","url":"https://github.com/AutoVision-cloud/SA-Det3D"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrians","slug":"3d-object-detection-on-kitti-pedestrians","dataset":"KITTI Pedestrians Moderate","dataset_url":"/dataset/kitti","rows_in_archive":12,"metrics":["AP"],"first_row_in_archive_order":{"model":"3D-FCT","paper_title":"3D-FCT: Simultaneous 3D Object Detection and Tracking Using Feature Correlation","paper_url":"/paper/3d-fct-simultaneous-3d-object-detection-and","paper_date":"2021-10-06","arxiv_id":"2110.02531","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-easy-val","slug":"3d-object-detection-on-kitti-cars-easy-val","dataset":"KITTI Cars Easy val","dataset_url":"/dataset/kitti","rows_in_archive":11,"metrics":["AP"],"first_row_in_archive_order":{"model":"SA-SSD+EBM","paper_title":"Accurate 3D Object Detection using Energy-Based Models","paper_url":"/paper/accurate-3d-object-detection-using-energy","paper_date":"2020-12-08","arxiv_id":"2012.04634","code_links":[{"title":"fregu856/ebms_3dod","url":"https://github.com/fregu856/ebms_3dod"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-moderate-1","slug":"3d-object-detection-on-kitti-cars-moderate-1","dataset":"KITTI Cars Moderate val","dataset_url":"/dataset/kitti","rows_in_archive":11,"metrics":["AP"],"first_row_in_archive_order":{"model":"SA-SSD+EBM","paper_title":"Accurate 3D Object Detection using Energy-Based Models","paper_url":"/paper/accurate-3d-object-detection-using-energy","paper_date":"2020-12-08","arxiv_id":"2012.04634","code_links":[{"title":"fregu856/ebms_3dod","url":"https://github.com/fregu856/ebms_3dod"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-nuscenes-camera-radar","slug":"3d-object-detection-on-nuscenes-camera-radar","dataset":"nuscenes Camera-Radar","dataset_url":"/dataset/nuscenes","rows_in_archive":11,"metrics":["NDS"],"first_row_in_archive_order":{"model":"SpaRC","paper_title":"SpaRC: Sparse Radar-Camera Fusion for 3D Object Detection","paper_url":"/paper/sparc-sparse-radar-camera-fusion-for-3d","paper_date":"2024-11-29","arxiv_id":"2411.19860","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-view-of-delft-val","slug":"3d-object-detection-on-view-of-delft-val","dataset":"View-of-Delft (val)","dataset_url":"/dataset/view-of-delft-1","rows_in_archive":11,"metrics":["mAP"],"first_row_in_archive_order":{"model":"HyDRa","paper_title":"Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perception","paper_url":"/paper/unleashing-hydra-hybrid-fusion-depth","paper_date":"2024-03-12","arxiv_id":"2403.07746","code_links":[{"title":"phi-wol/hydra","url":"https://github.com/phi-wol/hydra"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-cars-hard-val","slug":"3d-object-detection-on-kitti-cars-hard-val","dataset":"KITTI Cars Hard val","dataset_url":"/dataset/kitti","rows_in_archive":10,"metrics":["AP"],"first_row_in_archive_order":{"model":"M3DeTR","paper_title":"M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers","paper_url":"/paper/m3detr-multi-representation-multi-scale","paper_date":"2021-04-24","arxiv_id":"2104.11896","code_links":[{"title":"rayguan97/M3DeTR","url":"https://github.com/rayguan97/M3DeTR"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-dair-v2x-i","slug":"3d-object-detection-on-dair-v2x-i","dataset":"DAIR-V2X-I","dataset_url":"/dataset/dair-v2x","rows_in_archive":9,"metrics":["AP|R40(moderate)","AP|R40(easy)","AP|R40(hard)"],"first_row_in_archive_order":{"model":"MonoUNI","paper_title":"MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues","paper_url":"/paper/monouni-a-unified-vehicle-and-infrastructure","paper_date":"2023-09-21","arxiv_id":null,"code_links":[{"title":"Traffic-X/MonoUNI","url":"https://github.com/Traffic-X/MonoUNI"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrians-easy","slug":"3d-object-detection-on-kitti-pedestrians-easy","dataset":"KITTI Pedestrians Easy","dataset_url":"/dataset/kitti","rows_in_archive":9,"metrics":["AP"],"first_row_in_archive_order":{"model":"IPOD","paper_title":"IPOD: Intensive Point-based Object Detector for Point Cloud","paper_url":"/paper/ipod-intensive-point-based-object-detector","paper_date":"2018-12-13","arxiv_id":"1812.05276","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrians-hard","slug":"3d-object-detection-on-kitti-pedestrians-hard","dataset":"KITTI Pedestrians Hard","dataset_url":"/dataset/kitti","rows_in_archive":9,"metrics":["AP"],"first_row_in_archive_order":{"model":"SVGA-Net","paper_title":"SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds","paper_url":"/paper/svga-net-sparse-voxel-graph-attention-network","paper_date":"2020-06-07","arxiv_id":"2006.04043","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-rope3d","slug":"3d-object-detection-on-rope3d","dataset":"Rope3D","dataset_url":"/dataset/rope3d","rows_in_archive":8,"metrics":["AP@0.7"],"first_row_in_archive_order":{"model":"MonoUNI","paper_title":"MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues","paper_url":"/paper/monouni-a-unified-vehicle-and-infrastructure","paper_date":"2023-09-21","arxiv_id":null,"code_links":[{"title":"Traffic-X/MonoUNI","url":"https://github.com/Traffic-X/MonoUNI"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-sun-rgbd","slug":"3d-object-detection-on-sun-rgbd","dataset":"SUN-RGBD","dataset_url":"/dataset/sun-rgb-d","rows_in_archive":8,"metrics":["mAP@0.25","mAP@0.5","Inference Speed (s)"],"first_row_in_archive_order":{"model":"Uni3DETR","paper_title":"Uni3DETR: Unified 3D Detection Transformer","paper_url":"/paper/uni3detr-unified-3d-detection-transformer-1","paper_date":"2023-10-09","arxiv_id":"2310.05699","code_links":[{"title":"zhenyuw16/uni3detr","url":"https://github.com/zhenyuw16/uni3detr"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-waymo-open-dataset","slug":"3d-object-detection-on-waymo-open-dataset","dataset":"Waymo Open Dataset","dataset_url":"/dataset/waymo-open-dataset","rows_in_archive":8,"metrics":["mAPH/L2"],"first_row_in_archive_order":{"model":"LION","paper_title":"LION: Linear Group RNN for 3D Object Detection in Point Clouds","paper_url":"/paper/lion-linear-group-rnn-for-3d-object-detection","paper_date":"2024-07-25","arxiv_id":"2407.18232","code_links":[{"title":"happinesslz/LION","url":"https://github.com/happinesslz/LION"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-waymo-vehicle","slug":"3d-object-detection-on-waymo-vehicle","dataset":"waymo vehicle","dataset_url":"/dataset/waymo-open-dataset","rows_in_archive":8,"metrics":["APH/L2","AP","L1 mAP"],"first_row_in_archive_order":{"model":"PillarNeXt","paper_title":"PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds","paper_url":"/paper/pillarnext-rethinking-network-designs-for-3d","paper_date":"2023-05-08","arxiv_id":"2305.04925","code_links":[{"title":"qcraftai/pillarnext","url":"https://github.com/qcraftai/pillarnext"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-nuscenes-lidar-only","slug":"3d-object-detection-on-nuscenes-lidar-only","dataset":"nuScenes LiDAR only","dataset_url":"/dataset/nuscenes-lidar-only","rows_in_archive":7,"metrics":["NDS","NDS (val)","mAP","mAP (val)"],"first_row_in_archive_order":{"model":"LION","paper_title":"LION: Linear Group RNN for 3D Object Detection in Point Clouds","paper_url":"/paper/lion-linear-group-rnn-for-3d-object-detection","paper_date":"2024-07-25","arxiv_id":"2407.18232","code_links":[{"title":"happinesslz/LION","url":"https://github.com/happinesslz/LION"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-s3dis","slug":"3d-object-detection-on-s3dis","dataset":"S3DIS","dataset_url":"/dataset/s3dis","rows_in_archive":7,"metrics":["mAP@0.5","mAP@0.25"],"first_row_in_archive_order":{"model":"UniDet3D","paper_title":"UniDet3D: Multi-dataset Indoor 3D Object Detection","paper_url":"/paper/unidet3d-multi-dataset-indoor-3d-object","paper_date":"2024-09-06","arxiv_id":"2409.04234","code_links":[{"title":"filapro/unidet3d","url":"https://github.com/filapro/unidet3d"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-waymo-cyclist","slug":"3d-object-detection-on-waymo-cyclist","dataset":"waymo cyclist","dataset_url":"/dataset/waymo-open-dataset","rows_in_archive":7,"metrics":["APH/L2"],"first_row_in_archive_order":{"model":"DSVT(val)","paper_title":"DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets","paper_url":"/paper/dsvt-dynamic-sparse-voxel-transformer-with","paper_date":"2023-01-15","arxiv_id":"2301.06051","code_links":[{"title":"open-mmlab/mmdetection3d","url":"https://github.com/open-mmlab/mmdetection3d"},{"title":"open-mmlab/OpenPCDet","url":"https://github.com/open-mmlab/OpenPCDet"},{"title":"haiyang-w/dsvt","url":"https://github.com/haiyang-w/dsvt"},{"title":"happytianhao/tade","url":"https://github.com/happytianhao/tade"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-waymo-pedestrian","slug":"3d-object-detection-on-waymo-pedestrian","dataset":"waymo pedestrian","dataset_url":"/dataset/waymo-open-dataset","rows_in_archive":7,"metrics":["APH/L2"],"first_row_in_archive_order":{"model":"DSVT(val)","paper_title":"DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets","paper_url":"/paper/dsvt-dynamic-sparse-voxel-transformer-with","paper_date":"2023-01-15","arxiv_id":"2301.06051","code_links":[{"title":"open-mmlab/mmdetection3d","url":"https://github.com/open-mmlab/mmdetection3d"},{"title":"open-mmlab/OpenPCDet","url":"https://github.com/open-mmlab/OpenPCDet"},{"title":"haiyang-w/dsvt","url":"https://github.com/haiyang-w/dsvt"},{"title":"happytianhao/tade","url":"https://github.com/happytianhao/tade"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-argoverse","slug":"3d-object-detection-on-argoverse","dataset":"Argoverse","dataset_url":"/dataset/argoverse","rows_in_archive":6,"metrics":["AVG-CDS"],"first_row_in_archive_order":{"model":"tempVar","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-v2xset","slug":"3d-object-detection-on-v2xset","dataset":"V2XSet","dataset_url":"/dataset/v2xset","rows_in_archive":6,"metrics":["AP0.5 (Perfect)","AP0.7 (Perfect)","AP0.5 (Noisy)","AP0.7 (Noisy)"],"first_row_in_archive_order":{"model":"V2X-ViT","paper_title":"V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer","paper_url":"/paper/v2x-vit-vehicle-to-everything-cooperative","paper_date":"2022-03-20","arxiv_id":"2203.10638","code_links":[{"title":"DerrickXuNu/v2x-vit","url":"https://github.com/DerrickXuNu/v2x-vit"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-dttd2","slug":"3d-object-detection-on-dttd2","dataset":"DTTD-Mobile","dataset_url":"/dataset/dttd2","rows_in_archive":5,"metrics":["ADD AUC","ADD-S AUC"],"first_row_in_archive_order":{"model":"DTTDNet","paper_title":"Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset","paper_url":"/paper/towards-subcentimeter-accuracy-digital-twin","paper_date":"2023-09-24","arxiv_id":"2309.13570","code_links":[{"title":"augcog/dttdv1","url":"https://github.com/augcog/dttdv1"},{"title":"augcog/robust-digital-twin-tracking","url":"https://github.com/augcog/robust-digital-twin-tracking"},{"title":"augcog/dttd2","url":"https://github.com/augcog/dttd2"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-opv2v","slug":"3d-object-detection-on-opv2v","dataset":"OPV2V","dataset_url":"/dataset/opv2v","rows_in_archive":5,"metrics":["AP@0.7@Default","AP@0.7@CulverCity"],"first_row_in_archive_order":{"model":"V2VNet (PointPillar backbone)","paper_title":"V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction","paper_url":"/paper/v2vnet-vehicle-to-vehicle-communication-for","paper_date":"2020-08-17","arxiv_id":"2008.07519","code_links":[{"title":"DerrickXuNu/OpenCOOD","url":"https://github.com/DerrickXuNu/OpenCOOD"},{"title":"coperception/coperception","url":"https://github.com/coperception/coperception"},{"title":"taco-group/stamp","url":"https://github.com/taco-group/stamp"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/3d-object-detection-on-simbev","slug":"3d-object-detection-on-simbev","dataset":"SimBEV","dataset_url":"/dataset/simbev","rows_in_archive":5,"metrics":["SDS","mAP","mATE","mAOE","mASE","mAVE"],"first_row_in_archive_order":{"model":"UniTR+LSS","paper_title":"SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and Dataset","paper_url":"/paper/simbev-a-synthetic-multi-task-multi-sensor","paper_date":"2025-02-04","arxiv_id":"2502.01894","code_links":[{"title":"goodarzmehr/simbev","url":"https://github.com/goodarzmehr/simbev"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-v2x-sim","slug":"3d-object-detection-on-v2x-sim","dataset":"V2X-SIM","dataset_url":"/dataset/v2x-sim","rows_in_archive":5,"metrics":["mAP","mATE","mASE","mAOE"],"first_row_in_archive_order":{"model":"QUEST","paper_title":"QUEST: Query Stream for Practical Cooperative Perception","paper_url":"/paper/quest-query-stream-for-vehicle-infrastructure","paper_date":"2023-08-03","arxiv_id":"2308.01804","code_links":[{"title":"leofansq/QUEST","url":"https://github.com/leofansq/QUEST"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-aeo","slug":"3d-object-detection-on-aeo","dataset":"Aria Everyday Objects","dataset_url":"/dataset/aria-everyday-objects","rows_in_archive":4,"metrics":["mAP"],"first_row_in_archive_order":{"model":"EVL","paper_title":"EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models","paper_url":"/paper/efm3d-a-benchmark-for-measuring-progress","paper_date":"2024-06-14","arxiv_id":"2406.10224","code_links":[{"title":"facebookresearch/efm3d","url":"https://github.com/facebookresearch/efm3d"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-aria-synthetic","slug":"3d-object-detection-on-aria-synthetic","dataset":"Aria Synthetic Environments","dataset_url":"/dataset/aria-synthetic-environments","rows_in_archive":4,"metrics":["MAP"],"first_row_in_archive_order":{"model":"EVL","paper_title":"EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models","paper_url":"/paper/efm3d-a-benchmark-for-measuring-progress","paper_date":"2024-06-14","arxiv_id":"2406.10224","code_links":[{"title":"facebookresearch/efm3d","url":"https://github.com/facebookresearch/efm3d"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-arkitscenes","slug":"3d-object-detection-on-arkitscenes","dataset":"ARKitScenes","dataset_url":"/dataset/arkitscenes","rows_in_archive":4,"metrics":["mAP@0.25","mAP@0.5"],"first_row_in_archive_order":{"model":"UniDet3D","paper_title":"UniDet3D: Multi-dataset Indoor 3D Object Detection","paper_url":"/paper/unidet3d-multi-dataset-indoor-3d-object","paper_date":"2024-09-06","arxiv_id":"2409.04234","code_links":[{"title":"filapro/unidet3d","url":"https://github.com/filapro/unidet3d"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-cyclist-easy-val","slug":"3d-object-detection-on-kitti-cyclist-easy-val","dataset":"KITTI Cyclist Easy val","dataset_url":"/dataset/kitti","rows_in_archive":4,"metrics":["AP"],"first_row_in_archive_order":{"model":"M3DeTR","paper_title":"M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers","paper_url":"/paper/m3detr-multi-representation-multi-scale","paper_date":"2021-04-24","arxiv_id":"2104.11896","code_links":[{"title":"rayguan97/M3DeTR","url":"https://github.com/rayguan97/M3DeTR"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-kitti-cyclist-hard-val","slug":"3d-object-detection-on-kitti-cyclist-hard-val","dataset":"KITTI Cyclist Hard val","dataset_url":"/dataset/kitti","rows_in_archive":4,"metrics":["AP"],"first_row_in_archive_order":{"model":"M3DeTR","paper_title":"M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers","paper_url":"/paper/m3detr-multi-representation-multi-scale","paper_date":"2021-04-24","arxiv_id":"2104.11896","code_links":[{"title":"rayguan97/M3DeTR","url":"https://github.com/rayguan97/M3DeTR"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-kitti-cyclist-moderate","slug":"3d-object-detection-on-kitti-cyclist-moderate","dataset":"KITTI Cyclist Moderate val","dataset_url":"/dataset/kitti","rows_in_archive":4,"metrics":["AP"],"first_row_in_archive_order":{"model":"M3DeTR","paper_title":"M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers","paper_url":"/paper/m3detr-multi-representation-multi-scale","paper_date":"2021-04-24","arxiv_id":"2104.11896","code_links":[{"title":"rayguan97/M3DeTR","url":"https://github.com/rayguan97/M3DeTR"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrian","slug":"3d-object-detection-on-kitti-pedestrian","dataset":"KITTI Pedestrian Moderate val","dataset_url":"/dataset/kitti","rows_in_archive":4,"metrics":["AP"],"first_row_in_archive_order":{"model":"PVCNN","paper_title":"Point-Voxel CNN for Efficient 3D Deep Learning","paper_url":"/paper/point-voxel-cnn-for-efficient-3d-deep","paper_date":"2019-07-08","arxiv_id":"1907.03739","code_links":[{"title":"isl-org/Open3D-ML","url":"https://github.com/isl-org/Open3D-ML"},{"title":"mit-han-lab/pvcnn","url":"https://github.com/mit-han-lab/pvcnn"},{"title":"zghera/voxel-tf-ops","url":"https://github.com/zghera/voxel-tf-ops"},{"title":"zghera/pvcnn-tf","url":"https://github.com/zghera/pvcnn-tf"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":5}}},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrian-easy","slug":"3d-object-detection-on-kitti-pedestrian-easy","dataset":"KITTI Pedestrian Easy val","dataset_url":"/dataset/kitti","rows_in_archive":4,"metrics":["AP"],"first_row_in_archive_order":{"model":"PVCNN","paper_title":"Point-Voxel CNN for Efficient 3D Deep Learning","paper_url":"/paper/point-voxel-cnn-for-efficient-3d-deep","paper_date":"2019-07-08","arxiv_id":"1907.03739","code_links":[{"title":"isl-org/Open3D-ML","url":"https://github.com/isl-org/Open3D-ML"},{"title":"mit-han-lab/pvcnn","url":"https://github.com/mit-han-lab/pvcnn"},{"title":"zghera/voxel-tf-ops","url":"https://github.com/zghera/voxel-tf-ops"},{"title":"zghera/pvcnn-tf","url":"https://github.com/zghera/pvcnn-tf"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":5}}},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrian-hard","slug":"3d-object-detection-on-kitti-pedestrian-hard","dataset":"KITTI Pedestrian Hard val","dataset_url":"/dataset/kitti","rows_in_archive":4,"metrics":["AP"],"first_row_in_archive_order":{"model":"PVCNN","paper_title":"Point-Voxel CNN for Efficient 3D Deep Learning","paper_url":"/paper/point-voxel-cnn-for-efficient-3d-deep","paper_date":"2019-07-08","arxiv_id":"1907.03739","code_links":[{"title":"isl-org/Open3D-ML","url":"https://github.com/isl-org/Open3D-ML"},{"title":"mit-han-lab/pvcnn","url":"https://github.com/mit-han-lab/pvcnn"},{"title":"zghera/voxel-tf-ops","url":"https://github.com/zghera/voxel-tf-ops"},{"title":"zghera/pvcnn-tf","url":"https://github.com/zghera/pvcnn-tf"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":5}}},{"leaderboard":"/sota/3d-object-detection-on-truckscenes","slug":"3d-object-detection-on-truckscenes","dataset":"TruckScenes","dataset_url":"/dataset/truckscenes","rows_in_archive":4,"metrics":["NDS","mAP"],"first_row_in_archive_order":{"model":"SpaRC","paper_title":"SpaRC: Sparse Radar-Camera Fusion for 3D Object Detection","paper_url":"/paper/sparc-sparse-radar-camera-fusion-for-3d","paper_date":"2024-11-29","arxiv_id":"2411.19860","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-3d-object-detection-on","slug":"3d-object-detection-on-3d-object-detection-on","dataset":"3D Object Detection on Argoverse2 Camera Only","dataset_url":null,"rows_in_archive":3,"metrics":["Average mAP"],"first_row_in_archive_order":{"model":"Far3D","paper_title":"Far3D: Expanding the Horizon for Surround-view 3D Object Detection","paper_url":"/paper/far3d-expanding-the-horizon-for-surround-view","paper_date":"2023-08-18","arxiv_id":"2308.09616","code_links":[{"title":"megvii-research/far3d","url":"https://github.com/megvii-research/far3d"}],"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":8}}},{"leaderboard":"/sota/3d-object-detection-on-3rscan","slug":"3d-object-detection-on-3rscan","dataset":"3RScan","dataset_url":"/dataset/3r-scan","rows_in_archive":3,"metrics":["mAP@0.25","mAP@0.5"],"first_row_in_archive_order":{"model":"UniDet3D","paper_title":"UniDet3D: Multi-dataset Indoor 3D Object Detection","paper_url":"/paper/unidet3d-multi-dataset-indoor-3d-object","paper_date":"2024-09-06","arxiv_id":"2409.04234","code_links":[{"title":"filapro/unidet3d","url":"https://github.com/filapro/unidet3d"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-aimotive-dataset","slug":"3d-object-detection-on-aimotive-dataset","dataset":"aiMotive Dataset","dataset_url":"/dataset/aimotive-dataset","rows_in_archive":3,"metrics":["BEV AP@0.3 Highway","BEV AP@0.3 Night","BEV AP@0.3 Rain","BEV AP@0.3 Urban"],"first_row_in_archive_order":{"model":"Lidar-Radar-Camera","paper_title":"aiMotive Dataset: A Multimodal Dataset for Robust Autonomous Driving with Long-Range Perception","paper_url":"/paper/aimotive-dataset-a-multimodal-dataset-for","paper_date":"2022-11-17","arxiv_id":"2211.09445","code_links":[{"title":"aimotive/aimotive_dataset","url":"https://github.com/aimotive/aimotive_dataset"},{"title":"aimotive/mm_training","url":"https://github.com/aimotive/mm_training"},{"title":"aimotive/aimotive-dataset-loader","url":"https://github.com/aimotive/aimotive-dataset-loader"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-multiscan","slug":"3d-object-detection-on-multiscan","dataset":"MultiScan","dataset_url":"/dataset/multiscan","rows_in_archive":3,"metrics":["mAP@0.25","mAP@0.5"],"first_row_in_archive_order":{"model":"UniDet3D","paper_title":"UniDet3D: Multi-dataset Indoor 3D Object Detection","paper_url":"/paper/unidet3d-multi-dataset-indoor-3d-object","paper_date":"2024-09-06","arxiv_id":"2409.04234","code_links":[{"title":"filapro/unidet3d","url":"https://github.com/filapro/unidet3d"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-scannet-1","slug":"3d-object-detection-on-scannet-1","dataset":"ScanNet++","dataset_url":"/dataset/scannet-1","rows_in_archive":3,"metrics":["mAP@0.25","mAP@0.5"],"first_row_in_archive_order":{"model":"UniDet3D","paper_title":"UniDet3D: Multi-dataset Indoor 3D Object Detection","paper_url":"/paper/unidet3d-multi-dataset-indoor-3d-object","paper_date":"2024-09-06","arxiv_id":"2409.04234","code_links":[{"title":"filapro/unidet3d","url":"https://github.com/filapro/unidet3d"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-argoverse2","slug":"3d-object-detection-on-argoverse2","dataset":"Argoverse2","dataset_url":null,"rows_in_archive":2,"metrics":["mAP"],"first_row_in_archive_order":{"model":"LION","paper_title":"LION: Linear Group RNN for 3D Object Detection in Point Clouds","paper_url":"/paper/lion-linear-group-rnn-for-3d-object-detection","paper_date":"2024-07-25","arxiv_id":"2407.18232","code_links":[{"title":"happinesslz/LION","url":"https://github.com/happinesslz/LION"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-dair-v2x","slug":"3d-object-detection-on-dair-v2x","dataset":"DAIR-V2X","dataset_url":"/dataset/dair-v2x","rows_in_archive":2,"metrics":["AP50"],"first_row_in_archive_order":{"model":"CoBEVFlow","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-once","slug":"3d-object-detection-on-once","dataset":"ONCE","dataset_url":"/dataset/once","rows_in_archive":2,"metrics":[" mAP"],"first_row_in_archive_order":{"model":"LION","paper_title":"LION: Linear Group RNN for 3D Object Detection in Point Clouds","paper_url":"/paper/lion-linear-group-rnn-for-3d-object-detection","paper_date":"2024-07-25","arxiv_id":"2407.18232","code_links":[{"title":"happinesslz/LION","url":"https://github.com/happinesslz/LION"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-spiideo-soccernet","slug":"3d-object-detection-on-spiideo-soccernet","dataset":"Spiideo SoccerNet SynLoc","dataset_url":"/dataset/spiideo-soccernet-synloc","rows_in_archive":2,"metrics":["mAP-LocSim","FrameAccuracy","F1"],"first_row_in_archive_order":{"model":"Baseline-960x960","paper_title":"Spiideo SoccerNet SynLoc: Single Frame World Coordinate Athlete Detection and Localization with Synthetic Data","paper_url":"/paper/spiideo-soccernet-synloc-single-frame-world","paper_date":"2025-02-27","arxiv_id":null,"code_links":[{"title":"spiideo/sskit","url":"https://github.com/spiideo/sskit"},{"title":"Spiideo/mmpose","url":"https://github.com/Spiideo/mmpose"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-waymo-all-ns","slug":"3d-object-detection-on-waymo-all-ns","dataset":"waymo all_ns","dataset_url":"/dataset/waymo-open-dataset","rows_in_archive":2,"metrics":["APH/L2"],"first_row_in_archive_order":{"model":"CenterPoint","paper_title":"Center-based 3D Object Detection and Tracking","paper_url":"/paper/center-based-3d-object-detection-and-tracking","paper_date":"2020-06-19","arxiv_id":"2006.11275","code_links":[{"title":"open-mmlab/mmdetection3d","url":"https://github.com/open-mmlab/mmdetection3d"},{"title":"tianweiy/CenterPoint","url":"https://github.com/tianweiy/CenterPoint"},{"title":"nvidia-ai-iot/lidar_ai_solution","url":"https://github.com/nvidia-ai-iot/lidar_ai_solution"},{"title":"PaddlePaddle/Paddle3D","url":"https://github.com/PaddlePaddle/Paddle3D"},{"title":"livox-sdk/livox_detection","url":"https://github.com/livox-sdk/livox_detection"},{"title":"CarkusL/CenterPoint","url":"https://github.com/CarkusL/CenterPoint"},{"title":"tianweiy/CenterPoint-KITTI","url":"https://github.com/tianweiy/CenterPoint-KITTI"},{"title":"chowkamlee81/CentrePointNet","url":"https://github.com/chowkamlee81/CentrePointNet"},{"title":"zion-king/Center-based-3D-Object-Detection-and-Tracking","url":"https://github.com/zion-king/Center-based-3D-Object-Detection-and-Tracking"},{"title":"mon95/centerpoint-maps","url":"https://github.com/mon95/centerpoint-maps"},{"title":"15526837635/CenterPoint","url":"https://github.com/15526837635/CenterPoint"},{"title":"abhigoku10/CenterPoint_PC","url":"https://github.com/abhigoku10/CenterPoint_PC"},{"title":"safetylab24/FusionCVCP","url":"https://github.com/safetylab24/FusionCVCP"}],"syntology":{"n":22,"n_ran":12,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-cityscapes-3d","slug":"3d-object-detection-on-cityscapes-3d","dataset":"Cityscapes 3D","dataset_url":"/dataset/cityscapes-3d","rows_in_archive":1,"metrics":["mDS"],"first_row_in_archive_order":{"model":"TaskPrompter","paper_title":"Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth Estimation","paper_url":"/paper/joint-2d-3d-multi-task-learning-on-cityscapes","paper_date":"2023-04-03","arxiv_id":"2304.00971","code_links":[{"title":"prismformore/multi-task-transformer","url":"https://github.com/prismformore/multi-task-transformer"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-clear-weather","slug":"3d-object-detection-on-clear-weather","dataset":"Clear Weather","dataset_url":"/dataset/clear-weather","rows_in_archive":1,"metrics":["mod. Car AP@.7IoU"],"first_row_in_archive_order":{"model":"PV-RCNN","paper_title":"LiDAR Snowfall Simulation for Robust 3D Object Detection","paper_url":"/paper/lidar-snowfall-simulation-for-robust-3d","paper_date":"2022-03-28","arxiv_id":"2203.15118","code_links":[{"title":"syscv/lidar_snow_sim","url":"https://github.com/syscv/lidar_snow_sim"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-irv2v","slug":"3d-object-detection-on-irv2v","dataset":"IRV2V","dataset_url":"/dataset/irv2v","rows_in_archive":1,"metrics":["AP50","AP70"],"first_row_in_archive_order":{"model":"CoBEVFlow","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-cyclists-1","slug":"3d-object-detection-on-kitti-cyclists-1","dataset":"KITTI Cyclists Moderate val","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"Deformable PV-RCNN","paper_title":"Deformable PV-RCNN: Improving 3D Object Detection with Learned Deformations","paper_url":"/paper/deformable-pv-rcnn-improving-3d-object","paper_date":"2020-08-20","arxiv_id":"2008.08766","code_links":[{"title":"AutoVision-cloud/DeformablePVRCNN","url":"https://github.com/AutoVision-cloud/DeformablePVRCNN"},{"title":"AutoVision-cloud/Deformable-PV-RCNN","url":"https://github.com/AutoVision-cloud/Deformable-PV-RCNN"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrian-1","slug":"3d-object-detection-on-kitti-pedestrian-1","dataset":"KITTI Pedestrian Moderate","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["Average Precision"],"first_row_in_archive_order":{"model":"PiFeNet","paper_title":"Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar Network","paper_url":"/paper/pifenet-pillar-feature-network-for-real-time","paper_date":"2021-12-31","arxiv_id":"2112.15458","code_links":[{"title":"ldtho/pifenet","url":"https://github.com/ldtho/pifenet"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrian-2","slug":"3d-object-detection-on-kitti-pedestrian-2","dataset":"KITTI Pedestrian","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"PiFeNet","paper_title":"Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar Network","paper_url":"/paper/pifenet-pillar-feature-network-for-real-time","paper_date":"2021-12-31","arxiv_id":"2112.15458","code_links":[{"title":"ldtho/pifenet","url":"https://github.com/ldtho/pifenet"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrian-easy-1","slug":"3d-object-detection-on-kitti-pedestrian-easy-1","dataset":"KITTI Pedestrian Easy","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["Average Precision"],"first_row_in_archive_order":{"model":"PiFeNet","paper_title":"Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar Network","paper_url":"/paper/pifenet-pillar-feature-network-for-real-time","paper_date":"2021-12-31","arxiv_id":"2112.15458","code_links":[{"title":"ldtho/pifenet","url":"https://github.com/ldtho/pifenet"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrian-hard-1","slug":"3d-object-detection-on-kitti-pedestrian-hard-1","dataset":"KITTI Pedestrian Hard","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["Average Precision"],"first_row_in_archive_order":{"model":"PiFeNet","paper_title":"Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar Network","paper_url":"/paper/pifenet-pillar-feature-network-for-real-time","paper_date":"2021-12-31","arxiv_id":"2112.15458","code_links":[{"title":"ldtho/pifenet","url":"https://github.com/ldtho/pifenet"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-kitti-pedestrians-1","slug":"3d-object-detection-on-kitti-pedestrians-1","dataset":"KITTI Pedestrians Moderate val","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"Deformable PV-RCNN","paper_title":"Deformable PV-RCNN: Improving 3D Object Detection with Learned Deformations","paper_url":"/paper/deformable-pv-rcnn-improving-3d-object","paper_date":"2020-08-20","arxiv_id":"2008.08766","code_links":[{"title":"AutoVision-cloud/DeformablePVRCNN","url":"https://github.com/AutoVision-cloud/DeformablePVRCNN"},{"title":"AutoVision-cloud/Deformable-PV-RCNN","url":"https://github.com/AutoVision-cloud/Deformable-PV-RCNN"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-object-detection-on-light-snowfall","slug":"3d-object-detection-on-light-snowfall","dataset":"Light Snowfall","dataset_url":"/dataset/stf-light-snowfall","rows_in_archive":1,"metrics":["mod. Car AP@.7IoU"],"first_row_in_archive_order":{"model":"PV-RCNN","paper_title":"LiDAR Snowfall Simulation for Robust 3D Object Detection","paper_url":"/paper/lidar-snowfall-simulation-for-robust-3d","paper_date":"2022-03-28","arxiv_id":"2203.15118","code_links":[{"title":"syscv/lidar_snow_sim","url":"https://github.com/syscv/lidar_snow_sim"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-nuscenes-f","slug":"3d-object-detection-on-nuscenes-f","dataset":"nuScenes-F","dataset_url":null,"rows_in_archive":1,"metrics":["AP","AP50","AP75","AR","ARI","ARm","ARs"],"first_row_in_archive_order":{"model":"RRPN + R101 - F","paper_title":"RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles","paper_url":"/paper/rrpn-radar-region-proposal-network-for-object","paper_date":"2019-05-01","arxiv_id":"1905.00526","code_links":[{"title":"mrnabati/RRPN","url":"https://github.com/mrnabati/RRPN"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-nuscenes-fb","slug":"3d-object-detection-on-nuscenes-fb","dataset":"nuScenes-FB","dataset_url":null,"rows_in_archive":1,"metrics":["AP","AP50","AP75","AR","ARI","ARm","ARs"],"first_row_in_archive_order":{"model":"RRPN + R101 - FB","paper_title":"RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles","paper_url":"/paper/rrpn-radar-region-proposal-network-for-object","paper_date":"2019-05-01","arxiv_id":"1905.00526","code_links":[{"title":"mrnabati/RRPN","url":"https://github.com/mrnabati/RRPN"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-nyu-depth-v2","slug":"3d-object-detection-on-nyu-depth-v2","dataset":"NYU Depth v2","dataset_url":"/dataset/nyuv2","rows_in_archive":1,"metrics":["MAP"],"first_row_in_archive_order":{"model":"SGPN-CNN","paper_title":"SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation","paper_url":"/paper/sgpn-similarity-group-proposal-network-for-3d","paper_date":"2017-11-23","arxiv_id":"1711.08588","code_links":[{"title":"laughtervv/SGPN","url":"https://github.com/laughtervv/SGPN"}],"syntology":null}},{"leaderboard":"/sota/3d-object-detection-on-stf","slug":"3d-object-detection-on-stf","dataset":"Dense Fog","dataset_url":"/dataset/stf","rows_in_archive":1,"metrics":["mod. Car AP@.5IoU","mod. Cyclist AP@.25IoU","mod. Pedestrian AP@.25IoU","mod. mAP"],"first_row_in_archive_order":{"model":"PV-RCNN","paper_title":"Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather","paper_url":"/paper/fog-simulation-on-real-lidar-point-clouds-for","paper_date":"2021-08-11","arxiv_id":"2108.05249","code_links":[{"title":"MartinHahner/LiDAR_fog_sim","url":"https://github.com/MartinHahner/LiDAR_fog_sim"}],"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":6}}},{"leaderboard":"/sota/3d-object-detection-on-stf-heavy-snowfall","slug":"3d-object-detection-on-stf-heavy-snowfall","dataset":"Heavy Snowfall","dataset_url":"/dataset/stf-heavy-snow","rows_in_archive":1,"metrics":["mod. Car AP@.7IoU"],"first_row_in_archive_order":{"model":"PV-RCNN","paper_title":"LiDAR Snowfall Simulation for Robust 3D Object Detection","paper_url":"/paper/lidar-snowfall-simulation-for-robust-3d","paper_date":"2022-03-28","arxiv_id":"2203.15118","code_links":[{"title":"syscv/lidar_snow_sim","url":"https://github.com/syscv/lidar_snow_sim"}],"syntology":null}}],"datasets":[{"url":"/dataset/kitti","name":"KITTI","full_name":"","num_papers_in_archive":3661},{"url":"/dataset/nuscenes","name":"nuScenes","full_name":"","num_papers_in_archive":2139},{"url":"/dataset/scannet","name":"ScanNet","full_name":"","num_papers_in_archive":1595},{"url":"/dataset/nyuv2","name":"NYUv2","full_name":"NYU-Depth V2","num_papers_in_archive":986},{"url":"/dataset/s3dis","name":"S3DIS","full_name":"Stanford 3D Indoor Scene Dataset (S3DIS)","num_papers_in_archive":488},{"url":"/dataset/waymo-open-dataset","name":"Waymo Open Dataset","full_name":"","num_papers_in_archive":481},{"url":"/dataset/sun-rgb-d","name":"SUN RGB-D","full_name":"SUN RGB-D","num_papers_in_archive":477},{"url":"/dataset/argoverse","name":"Argoverse","full_name":"","num_papers_in_archive":386},{"url":"/dataset/argoverse-2","name":"Argoverse 2","full_name":"","num_papers_in_archive":185},{"url":"/dataset/hypersim","name":"Hypersim","full_name":"","num_papers_in_archive":108},{"url":"/dataset/once","name":"ONCE","full_name":"One Million Scenes","num_papers_in_archive":87},{"url":"/dataset/opv2v","name":"OPV2V","full_name":"","num_papers_in_archive":78},{"url":"/dataset/arkitscenes","name":"ARKitScenes","full_name":"","num_papers_in_archive":75},{"url":"/dataset/pandaset","name":"PandaSet","full_name":"","num_papers_in_archive":54},{"url":"/dataset/objectron","name":"Objectron","full_name":null,"num_papers_in_archive":48},{"url":"/dataset/3r-scan","name":"3RScan","full_name":"","num_papers_in_archive":44},{"url":"/dataset/h3d","name":"H3D","full_name":"Honda Research Institute 3D","num_papers_in_archive":39},{"url":"/dataset/dair-v2x","name":"DAIR-V2X","full_name":"","num_papers_in_archive":38},{"url":"/dataset/a-3d","name":"A*3D","full_name":null,"num_papers_in_archive":37},{"url":"/dataset/v2xset","name":"V2XSet","full_name":"","num_papers_in_archive":36},{"url":"/dataset/v2v4real","name":"V2V4Real","full_name":"","num_papers_in_archive":35},{"url":"/dataset/clear-weather","name":"Clear Weather","full_name":"DENSE","num_papers_in_archive":34},{"url":"/dataset/nuscenes-c","name":"nuScenes-C","full_name":"","num_papers_in_archive":33},{"url":"/dataset/v2x-sim","name":"V2X-SIM","full_name":"","num_papers_in_archive":32},{"url":"/dataset/kitti-c","name":"KITTI-C","full_name":"","num_papers_in_archive":30},{"url":"/dataset/scannet-1","name":"ScanNet++","full_name":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","num_papers_in_archive":25},{"url":"/dataset/cadc","name":"CADC","full_name":"Canadian Adverse Driving Conditions","num_papers_in_archive":23},{"url":"/dataset/k-radar","name":"K-Radar","full_name":"KAIST-Radar","num_papers_in_archive":23},{"url":"/dataset/stf","name":"Dense Fog","full_name":"DENSE","num_papers_in_archive":20},{"url":"/dataset/view-of-delft-1","name":"View-of-Delft","full_name":"","num_papers_in_archive":16},{"url":"/dataset/cityscapes-3d","name":"Cityscapes 3D","full_name":"","num_papers_in_archive":13},{"url":"/dataset/presil","name":"PreSIL","full_name":"Precise Synthetic Image and LiDAR","num_papers_in_archive":13},{"url":"/dataset/silk","name":"SILK","full_name":"Synth It Like KITTI","num_papers_in_archive":12},{"url":"/dataset/4d-or","name":"4D-OR","full_name":"","num_papers_in_archive":11},{"url":"/dataset/nuscenes-lidar-only","name":"nuScenes LiDAR only","full_name":"nuScenes LiDAR only","num_papers_in_archive":11},{"url":"/dataset/rope3d","name":"Rope3D","full_name":"","num_papers_in_archive":9},{"url":"/dataset/dttd2","name":"DTTD-Mobile","full_name":"","num_papers_in_archive":8},{"url":"/dataset/truckscenes","name":"TruckScenes","full_name":"MAN TruckScenes","num_papers_in_archive":8},{"url":"/dataset/dolphins","name":"DOLPHINS","full_name":"Dataset for Collaborative Perception enabled Harmonious and Interconnected Self-driving","num_papers_in_archive":7},{"url":"/dataset/rcooper","name":"RCooper","full_name":"Roadside Cooperative Perception Dataset","num_papers_in_archive":7},{"url":"/dataset/fat","name":"FAT","full_name":"Falling Things","num_papers_in_archive":6},{"url":"/dataset/aimotive-dataset","name":"aiMotive Dataset","full_name":"aiMotive Multimodal Dataset","num_papers_in_archive":5},{"url":"/dataset/aria-synthetic-environments","name":"Aria Synthetic Environments","full_name":"Aria Synthetic Environments","num_papers_in_archive":5},{"url":"/dataset/wod-c","name":"WOD-C","full_name":"","num_papers_in_archive":5},{"url":"/dataset/crashd","name":"CrashD","full_name":"","num_papers_in_archive":4},{"url":"/dataset/stf-heavy-snow","name":"Heavy Snowfall","full_name":"DENSE","num_papers_in_archive":4},{"url":"/dataset/multiscan","name":"MultiScan","full_name":"","num_papers_in_archive":4},{"url":"/dataset/mono3drefer","name":"Mono3DRefer","full_name":"","num_papers_in_archive":3},{"url":"/dataset/parcel2d-real","name":"Parcel2D Real","full_name":"","num_papers_in_archive":3},{"url":"/dataset/aria-digital-twin-dataset","name":"Aria Digital Twin Dataset","full_name":"Aria Digital Twin Dataset","num_papers_in_archive":2},{"url":"/dataset/stf-light-snowfall","name":"Light Snowfall","full_name":"DENSE","num_papers_in_archive":2},{"url":"/dataset/multiviewc","name":"MultiviewC","full_name":"","num_papers_in_archive":2},{"url":"/dataset/parcel3d","name":"Parcel3D","full_name":"","num_papers_in_archive":2},{"url":"/dataset/aria-everyday-objects","name":"Aria Everyday Objects","full_name":"Aria Everyday Objects","num_papers_in_archive":1},{"url":"/dataset/codd","name":"CODD","full_name":"Cooperative Driving Dataset","num_papers_in_archive":1},{"url":"/dataset/cy101-dataset","name":"CY101 Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/d2city","name":"D2City","full_name":"","num_papers_in_archive":1},{"url":"/dataset/irv2v","name":"IRV2V","full_name":"IRregular V2V Dataset","num_papers_in_archive":1},{"url":"/dataset/lidar-cs","name":"LiDAR-CS","full_name":"","num_papers_in_archive":1},{"url":"/dataset/motion-tracking-of-bionic-tendon-driven-robot","name":"Motion Tracking of Bionic Tendon-Driven Robot","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mvx","name":"MVX","full_name":"Multimodal V2X","num_papers_in_archive":1},{"url":"/dataset/remote-flash-lidar-vehicles-dataset","name":"Remote Flash LiDAR Vehicles Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/simbev","name":"SimBEV","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sotif-pcod","name":"SOTIF-PCOD","full_name":"SOTIF-related Use Case Dataset","num_papers_in_archive":1},{"url":"/dataset/spiideo-soccernet-synloc","name":"Spiideo SoccerNet SynLoc","full_name":"","num_papers_in_archive":1},{"url":"/dataset/human-palm-and-gloves-dataset-human-body","name":"Human Palm and Gloves Dataset | Human Body Parts Dataset","full_name":"","num_papers_in_archive":0},{"url":"/dataset/humans-in-3d","name":"Humans in 3D","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/3d-object-detection-from-stereo-images","name":"3D Object Detection From Stereo Images"},{"url":"/task/monocular-3d-object-detection","name":"Monocular 3D Object Detection"},{"url":"/task/multiview-detection","name":"Multiview Detection"},{"url":"/task/robust-3d-object-detection","name":"Robust 3D Object Detection"},{"url":"/task/robust-bev-detection","name":"Robust BEV Detection"}],"parent_tasks":[{"url":"/task/object-detection","name":"Object Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":764,"tagged_in_all":1576,"items":[{"url":"/paper/yolo9000-better-faster-stronger","title":"YOLO9000: Better, Faster, Stronger","date":"2016-12-25","arxiv_id":"1612.08242","repositories_listed":231,"syntology":{"n":60,"n_ran":17,"n_unverified":43,"n_pointer_only":22}},{"url":"/paper/objects-as-points","title":"Objects as Points","date":"2019-04-16","arxiv_id":"1904.07850","repositories_listed":76,"syntology":{"n":130,"n_ran":75,"n_unverified":55,"n_pointer_only":0}},{"url":"/paper/frustum-pointnets-for-3d-object-detection","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","date":"2017-11-22","arxiv_id":"1711.08488","repositories_listed":68,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/voxelnet-end-to-end-learning-for-point-cloud","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","date":"2017-11-17","arxiv_id":"1711.06396","repositories_listed":44,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/polyloss-a-polynomial-expansion-perspective-1","title":"PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions","date":"2022-04-26","arxiv_id":"2204.12511","repositories_listed":19,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/pointpillars-fast-encoders-for-object","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","date":"2018-12-14","arxiv_id":"1812.05784","repositories_listed":18,"syntology":{"n":15,"n_ran":2,"n_unverified":13,"n_pointer_only":1}},{"url":"/paper/nuscenes-a-multimodal-dataset-for-autonomous","title":"nuScenes: A multimodal dataset for autonomous driving","date":"2019-03-26","arxiv_id":"1903.11027","repositories_listed":16,"syntology":{"n":17,"n_ran":6,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/center-based-3d-object-detection-and-tracking","title":"Center-based 3D Object Detection and Tracking","date":"2020-06-19","arxiv_id":"2006.11275","repositories_listed":13,"syntology":{"n":22,"n_ran":12,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/deep-hough-voting-for-3d-object-detection-in","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","date":"2019-04-21","arxiv_id":"1904.09664","repositories_listed":13,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":10}},{"url":"/paper/pointrcnn-3d-object-proposal-generation-and","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","date":"2018-12-11","arxiv_id":"1812.04244","repositories_listed":13,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/pv-rcnn-point-voxel-feature-set-abstraction","title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","date":"2019-12-31","arxiv_id":"1912.13192","repositories_listed":12,"syntology":{"n":16,"n_ran":10,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/multimodal-token-fusion-for-vision","title":"Multimodal Token Fusion for Vision Transformers","date":"2022-04-19","arxiv_id":"2204.08721","repositories_listed":11,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/3d-bounding-box-estimation-using-deep","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","date":"2016-12-01","arxiv_id":"1612.00496","repositories_listed":11,"syntology":{"n":27,"n_ran":6,"n_unverified":21,"n_pointer_only":5}},{"url":"/paper/complex-yolo-real-time-3d-object-detection-on","title":"Complex-YOLO: Real-time 3D Object Detection on Point Clouds","date":"2018-03-16","arxiv_id":"1803.06199","repositories_listed":10,"syntology":null},{"url":"/paper/fcos3d-fully-convolutional-one-stage","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","date":"2021-04-22","arxiv_id":"2104.10956","repositories_listed":9,"syntology":{"n":22,"n_ran":13,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/multi-modality-cut-and-paste-for-3d-object","title":"Exploring Data Augmentation for Multi-Modality 3D Object Detection","date":"2020-12-23","arxiv_id":"2012.12741","repositories_listed":9,"syntology":null},{"url":"/paper/densefusion-6d-object-pose-estimation-by","title":"DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion","date":"2019-01-15","arxiv_id":"1901.04780","repositories_listed":8,"syntology":{"n":19,"n_ran":12,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/afdet-anchor-free-one-stage-3d-object","title":"AFDet: Anchor Free One Stage 3D Object Detection","date":"2020-06-23","arxiv_id":"2006.12671","repositories_listed":7,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/searching-efficient-3d-architectures-with","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","date":"2020-07-31","arxiv_id":"2007.16100","repositories_listed":6,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/part-a2-net-3d-part-aware-and-aggregation","title":"From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network","date":"2019-07-08","arxiv_id":"1907.03670","repositories_listed":6,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/voxel-r-cnn-towards-high-performance-voxel","title":"Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection","date":"2020-12-31","arxiv_id":"2012.15712","repositories_listed":5,"syntology":null},{"url":"/paper/cubeslam-monocular-3d-object-detection-and","title":"CubeSLAM: Monocular 3D Object SLAM","date":"2018-06-01","arxiv_id":"1806.00557","repositories_listed":5,"syntology":null},{"url":"/paper/octformer-octree-based-transformers-for-3d","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","date":"2023-05-04","arxiv_id":"2305.03045","repositories_listed":4,"syntology":{"n":9,"n_ran":6,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/dsvt-dynamic-sparse-voxel-transformer-with","title":"DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets","date":"2023-01-15","arxiv_id":"2301.06051","repositories_listed":4,"syntology":null},{"url":"/paper/fully-sparse-3d-object-detection","title":"Fully Sparse 3D Object Detection","date":"2022-07-20","arxiv_id":"2207.10035","repositories_listed":4,"syntology":null},{"url":"/paper/stcrowd-a-multimodal-dataset-for-pedestrian","title":"STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes","date":"2022-04-03","arxiv_id":"2204.01026","repositories_listed":4,"syntology":null},{"url":"/paper/group-free-3d-object-detection-via","title":"Group-Free 3D Object Detection via Transformers","date":"2021-04-01","arxiv_id":"2104.00678","repositories_listed":4,"syntology":{"n":17,"n_ran":9,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/generative-sparse-detection-networks-for-3d","title":"Generative Sparse Detection Networks for 3D Single-shot Object Detection","date":"2020-06-22","arxiv_id":"2006.12356","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/pointpainting-sequential-fusion-for-3d-object","title":"PointPainting: Sequential Fusion for 3D Object Detection","date":"2019-11-22","arxiv_id":"1911.10150","repositories_listed":4,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/m3d-rpn-monocular-3d-region-proposal-network","title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","date":"2019-07-13","arxiv_id":"1907.06038","repositories_listed":4,"syntology":{"n":21,"n_ran":5,"n_unverified":16,"n_pointer_only":0}}],"syntology_records":23,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}