How Robust is 3D Human Pose Estimation to Occlusion?

István Sárándi, Timm Linder, Kai O. Arras, Bastian Leibe
IEEE/RSJ International Conference on Intelligent Robots and Systems, Workshop on Robotic Co-workers 4.0 (IROSW) 2018

Occlusion is commonplace in realistic human-robot shared environments, yet its effects are not considered in standard 3D human pose estimation benchmarks. This leaves the question open: how robust are state-of-the-art 3D pose estimation methods against partial occlusions? We study several types of synthetic occlusions over the Human3.6M dataset and find a method with state-of-the-art benchmark performance to be sensitive even to low amounts of occlusion. Addressing this issue is key to progress in applications such as collaborative and service robotics. We take a first step in this direction by improving occlusion-robustness through training data augmentation with synthetic occlusions. This also turns out to be an effective regularizer that is beneficial even for non-occluded test cases.

» Show BibTeX

title={How Robust is {3D} Human Pose Estimation to Occlusion?},
author={S\'ar\'andi, Istv\'an and Linder, Timm and Arras, Kai O. and Leibe, Bastian},
booktitle={IEEE/RSJ International Conference on Intelligent Robots and Systems Workshops (IROSW)},

Disclaimer Home Visual Computing institute RWTH Aachen University