Fast 3D Pose Refinement with RGB Images
This addresses the need for efficient pose estimation on mobile robots with limited computing power, though it is incremental as it builds on existing coarse estimation methods.
The paper tackles the problem of slow and computationally intensive 3D pose estimation for robotics by proposing a CNN-based refinement system that uses coarse poses and bounding box images, achieving high precision on the YCB-Video dataset with minimal training data.
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.