GloPro: Globally-Consistent Uncertainty-Aware 3D Human Pose Estimation & Tracking in the Wild
This work addresses the need for safe human-robot interactions by providing globally-consistent uncertainty estimates, representing a novel method for a known bottleneck in 3D pose estimation.
The paper tackles the problem of uncertainty-aware 3D human pose estimation by introducing GloPro, a framework that predicts uncertainty distributions for body shape, pose, and root pose, and it demonstrates superior performance in human trajectory accuracy and real-time capability.
An accurate and uncertainty-aware 3D human body pose estimation is key to enabling truly safe but efficient human-robot interactions. Current uncertainty-aware methods in 3D human pose estimation are limited to predicting the uncertainty of the body posture, while effectively neglecting the body shape and root pose. In this work, we present GloPro, which to the best of our knowledge the first framework to predict an uncertainty distribution of a 3D body mesh including its shape, pose, and root pose, by efficiently fusing visual clues with a learned motion model. We demonstrate that it vastly outperforms state-of-the-art methods in terms of human trajectory accuracy in a world coordinate system (even in the presence of severe occlusions), yields consistent uncertainty distributions, and can run in real-time.