首页|DAMO: A Deep Solver for Arbitrary Marker Configuration in Optical Motion Capture
DAMO: A Deep Solver for Arbitrary Marker Configuration in Optical Motion Capture
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Assoc Computing Machinery
Marker-based optical motion capture (mocap) systems are increasinglyutilized for acquiring 3D human motion, offering advantages in capturingthe subtle nuances of human movement, style consistency, and ease ofobtaining desired motion. Motion data acquisition via mocap typicallyrequires laborious marker labeling and motion reconstruction, recentdeep-learning solutions have aimed to automate the process. However,such solutions generally presuppose a fixed marker configuration toreduce learning complexity, thereby limiting flexibility. To overcome thelimitation, we introduce DAMO, an end-to-end deep solver, proficientlyinferring arbitrary marker configurations and optimizing pose reconstruction.DAMO outperforms state-of-the-art like SOMA and MoCap-Solverin scenarios with significant noise and unknown marker configurations.We expect that DAMO will meet various practical demands such asfacilitating dynamic marker configuration adjustments during capturesessions, processing marker clouds irrespective of whether they employmixed or entirely unknown marker configurations, and allowing custommarker configurations to suit distinct capture scenarios.
NETL
NSTL
Assoc Computing Machinery
