Human Motion Prediction via Test-domain-aware Adaptation with Easily-available Human Motions Estimated from Videos
This addresses the data diversity issue in motion prediction for applications like animation or robotics, but it is incremental as it adapts existing methods with new data sources.
The paper tackles the problem of poor generalizability in 3D Human Motion Prediction due to limited motion capture data by enhancing models with additional learning using 3D motions estimated from easily available videos, resulting in demonstrated quantitative and qualitative improvements.
In 3D Human Motion Prediction (HMP), conventional methods train HMP models with expensive motion capture data. However, the data collection cost of such motion capture data limits the data diversity, which leads to poor generalizability to unseen motions or subjects. To address this issue, this paper proposes to enhance HMP with additional learning using estimated poses from easily available videos. The 2D poses estimated from the monocular videos are carefully transformed into motion capture-style 3D motions through our pipeline. By additional learning with the obtained motions, the HMP model is adapted to the test domain. The experimental results demonstrate the quantitative and qualitative impact of our method.