In contrast to previous work, MoSh solves for the Gether using sparse marker data by exploiting a parametric model of MoSh (Motion andShape capture), that automatically extracts thisĭetail from mocap data. We argue that important informationĪbout body surface motion is present in standard marker sets but is Marker-based motion capture (mocap) is widely criticized as pro-ĭucing lifeless animations. Level of realism that is difficult to achieve with standard skeleton-based mocap methods. MoSh needs only sparse mocap marker data to create animations (purple posed bodies) with a Split-color bodies compare the shapeĮstimated from sparse markers with scans. Bodies in purple are estimatedįrom 67 mocap markers, while scans in green are captured with a high-resolution 3D body scanner. Black‡ Max Planck Institute for Intelligent Systems, Tubingen, Germany ̈įigure 1: Shape from mocap computes body shape and pose from standard mocap marker sets. MoSh: Motion and Shape Capture from Sparse Markers Matthew Loper∗ Naureen Mahmood† Michael J.
0 Comments
Leave a Reply. |