Papers › Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations

Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations

18 Dec 2020CVPR 2021 1arXiv:2012.09988archive 2025-07-28

Adel Ahmadyan, Liangkai Zhang, Jianing Wei, Artsiom Ablavatski, Matthias Grundmann

3D object detection has recently become popular due to many applications in robotics, augmented reality, autonomy, and image retrieval. We introduce the Objectron dataset to advance the state of the art in 3D object detection and foster new research and applications, such as 3D object tracking, view synthesis, and improved 3D shape representation. The dataset contains object-centric short videos with pose annotations for nine categories and includes 4 million annotated images in 14,819 annotated videos. We also propose a new evaluation metric, 3D Intersection over Union, for 3D object detection. We demonstrate the usefulness of our dataset in 3D object detection tasks by providing baseline models trained on this dataset. Our dataset and evaluation source code are available online at http://www.objectron.dev

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

google-research-datasets/Objectron officialmentioned in papermentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Object Detection3D Object Tracking3D Shape RepresentationImage RetrievalMonocular 3D Object DetectionObjectObject DetectionObject TrackingRetrievalobject-detection

Datasets

Introduced by this paper, per the archive.

Objectron

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular 3D Object Detection Google Objectron EfficientNetLite + keypoint regressor AP at 10' Elevation error 0.8584 #2 of 3 Archive leaderboard report
Monocular 3D Object Detection Google Objectron EfficientNetLite + keypoint regressor AP at 15' Azimuth error 0.7844 #2 of 3 Archive leaderboard report
Monocular 3D Object Detection Google Objectron EfficientNetLite + keypoint regressor Average Precision at 0.5 3D IoU 0.6512 #2 of 3 Archive leaderboard report
Monocular 3D Object Detection Google Objectron EfficientNetLite + keypoint regressor MPE 0.0467 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientNetInverted Residual BlockPointwise ConvolutionRMSPropReLUSigmoid ActivationSqueeze-and-Excitation Block

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