{"url":"/dataset/nuscenes-lidar-only","name":"nuScenes LiDAR only","full_name":"nuScenes LiDAR only","description_markdown":"Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar. As machine learning based methods for detection and tracking become more prevalent, there is a need to train and evaluate such methods on datasets containing range sensor data along with images. In this work we present nuTonomy scenes (nuScenes), the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view. nuScenes comprises 1000 scenes, each 20s long and fully annotated with 3D bounding boxes for 23 classes and 8 attributes. It has 7x as many annotations and 100x as many images as the pioneering KITTI dataset. We define novel 3D detection and tracking metrics. We also provide careful dataset analysis as well as baselines for lidar and image based detection and tracking. Data, development kit and more information are available online.","description_withheld":null,"homepage":"https://www.nuscenes.org","introduced_date":"2019-03-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/nuscenes-a-multimodal-dataset-for-autonomous","title":"nuScenes: A multimodal dataset for autonomous driving","first_author":"Holger Caesar","url":null},"license":{"name":"Apache License, Version 2.0","url":"https://github.com/nutonomy/nuscenes-devkit/blob/master/LICENSE.txt"},"modalities":[{"name":"LiDAR","url":"/datasets/modality/lidar"}],"tasks":[{"name":"3D Object Detection","url":"/task/3d-object-detection","datasets_with_task":"/datasets/task/3d-object-detection"},{"name":"3D Multi-Object Tracking","url":"/task/3d-multi-object-tracking","datasets_with_task":"/datasets/task/3d-multi-object-tracking"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["nuScenes LiDAR only"],"data_loaders":[],"num_papers_in_archive":11,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-object-detection-on-nuscenes-lidar-only","task":"3D Object Detection","dataset_variant":"nuScenes LiDAR only","rows":7,"metrics":["NDS","NDS (val)","mAP","mAP (val)"],"first_row_in_archive_order":{"model":"LION","paper":"/paper/lion-linear-group-rnn-for-3d-object-detection","metrics":{"NDS":"73.9","NDS (val)":"72.1","mAP":"69.8","mAP (val)":"68.0"},"code_links":[{"title":"happinesslz/LION","url":"https://github.com/happinesslz/LION"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-multi-object-tracking-on-nuscenes-lidar","task":"3D Multi-Object Tracking","dataset_variant":"nuScenes LiDAR only","rows":1,"metrics":["AMOTA"],"first_row_in_archive_order":{"model":"VoxelNeXt","paper":"/paper/voxelnext-fully-sparse-voxelnet-for-3d-object-1","metrics":{"AMOTA":"71.0"},"code_links":[{"title":"dvlab-research/VoxelNeXt","url":"https://github.com/dvlab-research/VoxelNeXt"},{"title":"dvlab-research/3d-box-segment-anything","url":"https://github.com/dvlab-research/3d-box-segment-anything"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/lion-linear-group-rnn-for-3d-object-detection","title":"LION: Linear Group RNN for 3D Object Detection in Point Clouds","date":"2024-07-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/voxelnext-fully-sparse-voxelnet-for-3d-object-1","title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","date":"2023-03-20","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dsvt-dynamic-sparse-voxel-transformer-with","title":"DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets","date":"2023-01-15","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/pillarnet-high-performance-pillar-based-3d","title":"PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection","date":"2022-05-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/transfusion-robust-lidar-camera-fusion-for-3d","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","date":"2022-03-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/center-based-3d-object-detection-and-tracking","title":"Center-based 3D Object Detection and Tracking","date":"2020-06-19","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":22,"samples_ran":7,"samples_unverified":15,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/class-balanced-grouping-and-sampling-for","title":"Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection","date":"2019-08-26","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":22,"samples_ran":2,"samples_unverified":20,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pointpillars-fast-encoders-for-object","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","date":"2018-12-14","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":2,"samples_unverified":13,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":6,"samples_harvested":76,"samples_ran":13,"samples_unverified":63,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}