Imitrob：用于训练和评估6D物体姿态估计器的模仿学习数据集
Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose Estimators
AI总结：
本文提出Imitrob数据集，用于模仿学习中手持工具的6D姿态估计，包含多工具多任务的RGB图像及精确姿态真值，并验证了其有效性。
摘要：
本文介绍了一个数据集，用于训练和评估由标准RGB相机捕捉的任务演示中手持工具的6D姿态估计方法。尽管6D姿态估计方法取得了显著进展，但其在严重遮挡物体上的性能通常受限，这在模仿学习中很常见，因为物体通常被操作手部分遮挡。目前缺乏能在此类条件下开发鲁棒6D姿态估计方法的数据集。为解决此问题，我们收集了一个新数据集（Imitrob），旨在用于模仿学习及其他人类手持工具执行任务的场景中的6D姿态估计。该数据集包含九种不同工具和十二种操作任务的图像序列，具有两个相机视角、四名人类受试者以及左/右手。每张图像均附有通过HTC Vive运动追踪设备获得的6D物体姿态的精确真值测量。通过在各种设置下训练和评估最近的6D物体姿态估计方法（DOPE），展示了该数据集的使用。
英文摘要：
This paper introduces a dataset for training and evaluating methods for 6D pose estimation of hand-held tools in task demonstrations captured by a standard RGB camera. Despite the significant progress of 6D pose estimation methods, their performance is usually limited for heavily occluded objects, which is a common case in imitation learning, where the object is typically partially occluded by the manipulating hand. Currently, there is a lack of datasets that would enable the development of robust 6D pose estimation methods for these conditions. To overcome this problem, we collect a new dataset (Imitrob) aimed at 6D pose estimation in imitation learning and other applications where a human holds a tool and performs a task. The dataset contains image sequences of nine different tools and twelve manipulation tasks with two camera viewpoints, four human subjects, and left/right hand. Each image is accompanied by an accurate ground truth measurement of the 6D object pose obtained by the HTC Vive motion tracking device. The use of the dataset is demonstrated by training and evaluating a recent 6D object pose estimation method (DOPE) in various setups.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
