English

Fast 3D Pose Refinement with RGB Images

Computer Vision and Pattern Recognition 2019-11-19 v1

Abstract

Pose estimation is a vital step in many robotics and perception tasks such as robotic manipulation, autonomous vehicle navigation, etc. Current state-of-the-art pose estimation methods rely on deep neural networks with complicated structures and long inference times. While highly robust, they require computing power often unavailable on mobile robots. We propose a CNN-based pose refinement system which takes a coarsely estimated 3D pose from a computationally cheaper algorithm along with a bounding box image of the object, and returns a highly refined pose. Our experiments on the YCB-Video dataset show that our system can refine 3D poses to an extremely high precision with minimal training data.

Keywords

Cite

@article{arxiv.1911.07347,
  title  = {Fast 3D Pose Refinement with RGB Images},
  author = {Abhinav Jain and Frank Dellaert},
  journal= {arXiv preprint arXiv:1911.07347},
  year   = {2019}
}
R2 v1 2026-06-23T12:18:36.677Z