论文标题
Objectron：野外以姿势注释中以对象为中心视频的大型数据集
Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations
论文作者
论文摘要
由于在机器人技术，增强现实，自主权和图像检索中的许多应用中，3D对象检测最近变得流行。我们介绍了Objectron数据集，以在3D对象检测中推进最新技术，并培养新的研究和应用程序，例如3D对象跟踪，查看合成和改进的3D形状表示。该数据集包含以对象为中心的简短视频，其中包含9个类别的姿势注释，并在14,819个带注释的视频中包含400万个注释的图像。我们还提出了一个新的评估指标，即联合的3D交集，以进行3D对象检测。我们通过在此数据集上提供了训练的基线模型来证明数据集中数据集中的有用性。我们的数据集和评估源代码可在http://www.objectron.dev上在线获得。
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
