Measuring Physical Plausibility of 3D Human Poses Using Physics Simulation
This work addresses the limitation of standard accuracy metrics in 3D human pose estimation by providing a method to assess physical plausibility, which is important for applications like augmented reality and sports analysis, but it is incremental as it builds on existing plausibility metrics.
The paper tackles the problem of evaluating the physical plausibility of 3D human poses by proposing new metrics based on physics simulation, which correlate with existing plausibility metrics and measure stability during motion, using the Human3.6m dataset for evaluation.
Modeling humans in physical scenes is vital for understanding human-environment interactions for applications involving augmented reality or assessment of human actions from video (e.g. sports or physical rehabilitation). State-of-the-art literature begins with a 3D human pose, from monocular or multiple views, and uses this representation to ground the person within a 3D world space. While standard metrics for accuracy capture joint position errors, they do not consider physical plausibility of the 3D pose. This limitation has motivated researchers to propose other metrics evaluating jitter, floor penetration, and unbalanced postures. Yet, these approaches measure independent instances of errors and are not representative of balance or stability during motion. In this work, we propose measuring physical plausibility from within physics simulation. We introduce two metrics to capture the physical plausibility and stability of predicted 3D poses from any 3D Human Pose Estimation model. Using physics simulation, we discover correlations with existing plausibility metrics and measuring stability during motion. We evaluate and compare the performances of two state-of-the-art methods, a multi-view triangulated baseline, and ground truth 3D markers from the Human3.6m dataset.