High Performance Visual Pose Computation
MCML Authors
Benjamin Busam
Prof. Dr.
Principal Investigator
Abstract
Benjamin Busam
Prof. Dr.
Principal Investigator
Abstract
An outside-in system uses binocular stereo and a probabilistic sparse point cloud matcher to track objects with micrometre precision in real-time. Miniaturizing the system results in a markerless inside-out stereo method with improved rotational accuracy. Reducing the constraints, we reformulate marker-free monocular pose estimation as an action decision process where the next best pose is determined using a render-and-compare strategy. This allows instance agnostic pose estimation that generalizes to unseen objects. The methods are applied on a set of medical and industrial applications.
BibTeXKey: Bus21