</> Code with Papers by Syntology

Datasets › Waymo Open Dataset

Waymo Open Dataset

Introduced by Pei Sun et al. in Scalability in Perception for Autonomous Driving: Waymo Open Dataset archive 2025-07-28

The Waymo Open Dataset is comprised of high resolution sensor data collected by autonomous vehicles operated by the Waymo Driver in a wide variety of conditions.

The Waymo Open Dataset currently contains 1,950 segments. The authors plan to grow this dataset in the future. Currently the datasets includes:

  • 1,950 segments of 20s each, collected at 10Hz (390,000 frames) in diverse geographies and conditions
  • Sensor data
    • 1 mid-range lidar
    • 4 short-range lidars
    • 5 cameras (front and sides)
    • Synchronized lidar and camera data
    • Lidar to camera projections
    • Sensor calibrations and vehicle poses
  • Labeled data
    • Labels for 4 object classes - Vehicles, Pedestrians, Cyclists, Signs
    • High-quality labels for lidar data in 1,200 segments
    • 12.6M 3D bounding box labels with tracking IDs on lidar data
    • High-quality labels for camera data in 1,000 segments
    • 11.8M 2D bounding box labels with tracking IDs on camera data
HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 16 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
3D Multi-Object Tracking Waymo Open Dataset: Vehicle (Online Methods) RobMOT MOTA/L2 0.7466 RobMOT: Robust 3D Multi-Object Tracking by Observational... MohamedNagyMostafa/RobMOT 16 Compare
Object Detection Waymo 2D detection all_ns f0val YOLOX-L COCO-style AP 41.6 USB: Universal-Scale Object Detection Benchmark shinya7y/UniverseNet 15 Compare
3D Object Detection Waymo Open Dataset LION mAPH/L2 74.0 LION: Linear Group RNN for 3D Object Detection in Point Clouds happinesslz/LION 8 Compare
3D Object Detection waymo vehicle PillarNeXt APH/L2 75.76 PillarNeXt: Rethinking Network Designs for 3D Object... qcraftai/pillarnext 8 Compare
3D Object Detection waymo cyclist DSVT(val) APH/L2 78.0 DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets open-mmlab/mmdetection3d +3 7 Compare
3D Object Detection waymo pedestrian DSVT(val) APH/L2 76.4 DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets open-mmlab/mmdetection3d +3 7 Compare
Object Detection Waymo Open Dataset LeapMotor_Det AP/L2 70.41 2nd Place Solution for Waymo Open Dataset Challenge -... WongKinYiu/yolor 5 Compare
Unsupervised Panoptic Segmentation Waymo Open Dataset CUPS (54 pseudo-classes) PQ 27.3 Scene-Centric Unsupervised Panoptic Segmentation visinf/cups 4 Compare
3D Multi-Object Tracking Waymo Open Dataset DetZero MOTA/L2 0.7505 DetZero: Rethinking Offboard 3D Object Detection with... pjlab-adg/detzero 3 Compare
3D Object Detection From Monocular Images Waymo Open Dataset DEVIANT 3D mAPH Vehicle (Front Camera Only) 2.52 DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D... abhi1kumar/deviant +1 3 Compare
3D Object Detection waymo all_ns CenterPoint APH/L2 71.93 Center-based 3D Object Detection and Tracking open-mmlab/mmdetection3d +12 2 Compare
3D Semantic Segmentation Waymo Open Dataset DITR mIoU 73.3 DINO in the Room: Leveraging 2D Foundation Models for 3D... VisualComputingInstitute/DITR 2 Compare
Multiple Object Tracking Waymo Open Dataset QDTrack Category Vehicle Quasi-Dense Similarity Learning for Multiple Object Tracking SysCV/qdtrack +2 2 Compare
3D Human Pose Estimation Waymo Open Dataset VoxelKP MPJPE 8.87 VoxelKP: A Voxel-based Network Architecture for Human... shijianjian/voxelkp 1 Compare
Object Detection Waymo 2D detection all_ns test UniverseNet AP/L2 67.42 USB: Universal-Scale Object Detection Benchmark shinya7y/UniverseNet 1 Compare
Video Object Detection Waymo Open Dataset AP 59.28 Objects do not disappear: Video object detection by... l-kid/video-object-detection-by-location-anticipation +1 1 Compare

Papers archive 2025-07-28

30 shown of 34 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 481. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Scene-Centric Unsupervised Panoptic Segmentation 1 3 2 Apr 2025 ran 0 of 8 samples (8 unverified)
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation 1 1 24 Mar 2025 not harvested
MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving 1 1 23 Sep 2024 not harvested
vFusedSeg3D: 3rd Place Solution for 2024 Waymo Open Dataset Challenge in Semantic Segmentation 1 1 9 Aug 2024 not harvested
Do You Remember . . . the Future? Weak-to-Strong generalization in 3D Object Detection 1 1 3 Aug 2024 not harvested
LION: Linear Group RNN for 3D Object Detection in Point Clouds 1 1 25 Jul 2024 ran 0 of 7 samples (7 unverified)
RobMOT: Robust 3D Multi-Object Tracking by Observational Noise and State Estimation Drift Mitigation on LiDAR PointCloud 1 1 19 May 2024 not harvested
AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understanding 1 1 27 Feb 2024 not harvested
Unsupervised Universal Image Segmentation 2 1 28 Dec 2023 ran 13 of 15 samples (2 unverified)
VoxelKP: A Voxel-based Network Architecture for Human Keypoint Estimation in LiDAR Data 1 1 11 Dec 2023 not harvested
HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds 1 1 31 Oct 2023 not harvested
Objects do not disappear: Video object detection by single-frame object location anticipation 2 1 9 Aug 2023 not harvested
FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels 2 1 7 Aug 2023 not harvested
DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds 1 1 9 Jun 2023 ran 1 of 8 samples (7 unverified)
PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds 1 3 8 May 2023 not harvested
DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets 4 4 15 Jan 2023 not harvested
CenterFormer: Center-based Transformer for 3D Object Detection 1 4 12 Sep 2022 ran 5 of 6 samples (1 unverified)
DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection 2 1 21 Jul 2022 ran 9 of 15 samples (6 unverified)
SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking 6 1 8 Mar 2022 not harvested
Embracing Single Stride 3D Object Detector with Sparse Transformer 2 3 13 Dec 2021 not harvested
Immortal Tracker: Tracklet Never Dies 1 1 26 Nov 2021 not harvested
Voxel Transformer for 3D Object Detection 1 1 6 Sep 2021 ran 0 of 7 samples (7 unverified; 7 pointer-only for licence)
Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection 1 1 6 Sep 2021 ran 1 of 4 samples (3 unverified; 4 pointer-only for licence)
Geometry Uncertainty Projection Network for Monocular 3D Object Detection 1 1 29 Jul 2021 ran 8 of 21 samples (13 unverified)
2nd Place Solution for Waymo Open Dataset Challenge - Real-time 2D Object Detection 1 5 16 Jun 2021 not harvested
M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers 1 3 24 Apr 2021 ran 0 of 7 samples (7 unverified)
USB: Universal-Scale Object Detection Benchmark 1 16 25 Mar 2021 not harvested
PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection 1 1 31 Jan 2021 not harvested
Center-based 3D Object Detection and Tracking 13 4 19 Jun 2020 ran 7 of 22 samples (15 unverified)
Quasi-Dense Similarity Learning for Multiple Object Tracking 3 1 11 Jun 2020 not harvested

The full list of 34 is in the JSON twin.

Dataset loaders archive 2025-07-28

open-mmlab/mmdetection3dopen-mmlab/mmdetection3dpytorch
www.tensorflow.org/datasets/catalog/waymo_open_datasettensorflow/datasetstfjax
Pointcept/Pointceptpytorch

3 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Object Detection3D Object Detection3D Human Pose Estimation3D Semantic SegmentationMultiple Object TrackingAutonomous DrivingVideo Object DetectionUnsupervised Panoptic Segmentation3D Multi-Object Tracking3D Object Detection From Monocular Images

License archive 2025-07-28

Custom (non-commercial)

Modalities archive 2025-07-28

Images3DLiDAR

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • Waymo Open Dataset: Vehicle (Online Methods)
  • Waymo 2D detection all_ns f0val
  • Waymo 2D detection all_ns test
  • waymo vehicle
  • waymo pedestrian
  • waymo cyclist
  • waymo all_ns
  • Waymo Open Dataset

8 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections