MP6D: An RGB-D Dataset for Metal Parts’ 6D Pose Estimation

Abstract

We introduce MP6D, a public dataset which is used for 6D pose estimation of Metal Parts in industrial environments. The dataset consists of 20 metal parts made of aluminum alloy material which are commonly used in factories. To the best of our knowledge, this is the first dataset of metal parts with simultaneous multi-target, occluded, and illumination changes. The color homogeneity, textureless and light-reflecting properties raise great challenges for estimating the pose of the objects. To improve the accuracy of the ground-truth pose, we propose a novel bi-directional optimization method to minimize the projection errors of all the objects in the dataset. Our main insight is to iteratively optimize the union pose of multi-object in single-frame and the relative pose of each single object with respect to the Aurco-board through multi-frame information. We compare our dataset with several well-known pose estimation datasets. The results demonstrate that the accuracy of our dataset is superior to the others. We also provide the baselines for some state-of-the-art pose estimation methods upon our dataset for the comparison of further studies.