2018
Detect Globally, Label Locally: Learning Accurate 6-DOF Object Pose Estimation by Joint Segmentation and Coordinate Regression
RA-L 2018
Coordinate regression has established itself as one of the most successful current trends in model-based 6 degree of freedom (6-DOF) object pose estimation from a single image. The underlying idea is to train a system that can regress the three-dimensional coordinates of an object, given an input RG