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

2020/12/17 by Adel Ahmadyan, Liangkai Zhang, Ahmadyan, Adel +7 · 14 citations
Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Robotics and Sensor-Based Localization

paper · pdf · doi:10.48550/arxiv.2012.09988

openalex publication_date 2020/12/17 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

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

Cited by

• Orient Anything V2: Unifying Orientation and Rotation Understanding
• 4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer
• UAV-MM3D: A Large-Scale Synthetic Benchmark for 3D Perception of Unmanned Aerial Vehicles with Multi-Modal Data
• LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight
• DetAny4D: Detect Anything 4D Temporally in a Streaming RGB Video
• LAA3D: A Benchmark of Detecting and Tracking Low-Altitude Aircraft in 3D Space
• SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation
• iFlyBot-VLM Technical Report
• Visual Spatial Tuning
• Neural USD: An object-centric framework for iterative editing and control
• Monocular Visual 8D Pose Estimation for Articulated Bicycles and Cyclists
• MultiCOIN: Multi-Modal COntrollable Video INbetweening
• Robotic Manipulation Framework Based on Semantic Keypoints for Packing Shoes of Different Sizes, Shapes, and Softness
• 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection

Related

• Falling Things: A Synthetic Dataset for 3D Object Detection and Pose\n Estimation
• Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild
• Learning 3D Object Categories by Looking Around Them
• UnCommon Objects in 3D
• Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Images