SOMA: Solving Optical Marker-Based MoCap Automatically
Nima Ghorbani Michael J. Black
Max Planck Institute for Intelligent Systems, Tubingen, Germany
{nghorbani,black}@tuebingen.mpg.de
Figure 1: SOMA transforms raw motion capture (mocap) point clouds (black dots) to labeled markers (colored dots). The
cubes in yellow are detected “ghost” points; e.g. spurious reflections, non-body markers, or unidentified points. With labeled
mocap we fit ...


雷达卡




京公网安备 11010802022788号







