Estimating 6D Pose From Localizing Designated Surface Keypoints

TL;DR

This paper introduces a surface keypoint-based method for 6D pose estimation from RGB images that achieves high accuracy without post-processing, handles occlusion well, and improves ADD accuracy significantly.

Contribution

It proposes a novel keypoint detection approach on object surfaces for 6D pose estimation that outperforms existing CNN-based methods without requiring refinement.

Findings

Achieves 30% relative improvement in ADD accuracy without refinement

Handles heavy occlusion effectively by selecting confident keypoints

Provides competitive accuracy with simpler, faster processing

Abstract

In this paper, we present an accurate yet effective solution for 6D pose estimation from an RGB image. The core of our approach is that we first designate a set of surface points on target object model as keypoints and then train a keypoint detector (KPD) to localize them. Finally a PnP algorithm can recover the 6D pose according to the 2D-3D relationship of keypoints. Different from recent state-of-the-art CNN-based approaches that rely on a time-consuming post-processing procedure, our method can achieve competitive accuracy without any refinement after pose prediction. Meanwhile, we obtain a 30% relative improvement in terms of ADD accuracy among methods without using refinement. Moreover, we succeed in handling heavy occlusion by selecting the most confident keypoints to recover the 6D pose. For the sake of reproducibility, we will make our code and models publicly available soon.