How Robust is 3D Human Pose Estimation to Occlusion?
This addresses a critical problem for collaborative and service robotics by highlighting and mitigating occlusion sensitivity, though it is incremental as it builds on existing methods with data augmentation.
The study investigated the robustness of state-of-the-art 3D human pose estimation methods to partial occlusions, finding that a top-performing method was sensitive even to low occlusion levels, and improved robustness through synthetic occlusion data augmentation, which also acted as an effective regularizer for non-occluded cases.
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.