Fast Neural Inverse Kinematics on Human Body Motions
This work addresses the computational bottleneck in markerless motion capture for applications requiring real-time tracking, but it appears incremental as it builds on existing neural methods without introducing a new paradigm.
The paper tackles the problem of slow inference in markerless motion capture by developing a fast neural inverse kinematics framework for real-time human body motion tracking from 3D keypoints, achieving real-time performance.
Markerless motion capture enables the tracking of human motion without requiring physical markers or suits, offering increased flexibility and reduced costs compared to traditional systems. However, these advantages often come at the expense of higher computational demands and slower inference, limiting their applicability in real-time scenarios. In this technical report, we present a fast and reliable neural inverse kinematics framework designed for real-time capture of human body motions from 3D keypoints. We describe the network architecture, training methodology, and inference procedure in detail. Our framework is evaluated both qualitatively and quantitatively, and we support key design decisions through ablation studies.