The conventional pose estimation of a 3D object usually requires the knowledge of the 3D model of the object. Even with the recent development in convolutional neural networks (CNNs), a 3D model is often necessary in the final estimation. In this paper, we propose a two-stage pipeline that takes in raw colored point cloud data and estimates an object's translation and rotation by running 3D convolutions on voxels. The pipeline is simple yet highly accurate: translation error is reduced to the voxel resolution (around 1 cm) and rotation error is around 5 degrees. The pipeline is also put to actual robotic grasping tests where it achieves above 90% success rate for test objects. Another innovation is that a motion capture system is used to automatically label the point cloud samples which makes it possible to rapidly collect a large amount of highly accurate real data for training the neural networks.
@article{arxiv.1812.11284,
title = {3D Convolution on RGB-D Point Clouds for Accurate Model-free Object Pose Estimation},
author = {Zhongang Cai and Cunjun Yu and Quang-Cuong Pham},
journal= {arXiv preprint arXiv:1812.11284},
year = {2019}
}