On End-To-End 6DoF Object Pose Estimation and Robustness to Object Scale

Abstract

This report contains a set of experiments that seek to reproduce the claims of two recent works related to keypoint estimation, one specific to 6DoF object pose estimation, and the other presenting a generic architectural improvement for keypoint estimation but demonstrated in human pose estimation. More specifically, in the backpropagatable PnP, the authors claim that incorporating geometric optimization in a deep-learning pipeline and predicting an object's pose in an end-to-end manner yields improved performance. On the other hand, HigherHRNet introduces a novel heatmap aggregation method that allows for scale-aware pose estimations, offering higher keypoint localization accuracy for small scale objects.