Geometric Deep Learning for Pose Estimation
Theory and Pytorch Implementation Tutorial to find Object Pose from Single Monocular Image
Published in
6 min readMay 18, 2019
One of the central problems in Computer Vision and Robotics is that of understanding how objects are positioned with respect to the robot or the environment. In this post, I will explain the theory behind and give a pytorch implementation tutorial of the paper “6-DoF Object Pose from Semantic Keypoints” by Pavlakos et al.