Pose estimation of 3D objects in monocular images is a fundamental and long-standing
problem in computer vision. Existing deep learning approaches for 6D pose estimation …

Object pose distribution estimation is crucial in robotics for better path planning and
handling of symmetric objects. Recent distribution estimation approaches employ …

Object Pose Estimation is a crucial component in robotic gras** and augmented reality.
Learning based approaches typically require training data from a highly accurate CAD …

In this paper, we propose a novel encoder-decoder architecture, named SABER, to learn the
6D pose of the object in the embedding space by learning shape representation at a given …