MoCapAnything reconstructs asset-specific BVH animations from monocular video by predicting 3D joint trajectories then applying constraint-aware inverse kinematics guided by a reference prompt encoder.
Explicit box detection unifies end-to-end multi-person pose estimation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
citing papers explorer
-
MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos
MoCapAnything reconstructs asset-specific BVH animations from monocular video by predicting 3D joint trajectories then applying constraint-aware inverse kinematics guided by a reference prompt encoder.
- ScaleHP: Scale-Mediated Optimization of Coupled Errors for Metric-Space Hand Pose Estimation