Occlusion-Robust Object Pose Estimation with Holistic Representation

Practical object pose estimation demands robustness against occlusions to the target object. State-of-the-art (SOTA) object pose estimators take a two-stage approach, where the first stage predicts 2D landmarks using a deep network and the second stage solves for 6DOF pose from 2D-3D correspondences. Albeit widely adopted, such two-stage approaches could suffer from novel occlusions when generalising and weak landmark coherence due to disrupted features. To address these issues, we develop a novel occlude-and-blackout batch augmentation technique to learn occlusion-robust deep features, and a multi-precision supervision architecture to encourage holistic pose representation learning for accurate and coherent landmark predictions. We perform careful ablation tests to verify the impact of our innovations and compare our method to SOTA pose estimators. Without the need of any post-processing or refinement, our method exhibits superior performance on the LINEMOD dataset. On the YCB-Video dataset our method outperforms all non-refinement methods in terms of the ADD(-S) metric. We also demonstrate the high data-efficiency of our method. Our code is available at http://github.com/BoChenYS/ROPE

1. Introduction

Object pose estimation is the task of inferring the relative orientation and position between the target object and the observer. Such inference is crucial in many vision applications such as robotic manipulation [67], [66], [11], augmented reality [39], [12], autonomous driving [10], [61], [63] and spacecraft navigation [6], [49]. The problem can be simplified if depth information is available [40], [58], [17], [9]. However, depth sensors are not always practical. Pose estimation from images is thus an important research problem.