Model based full body human motion reconstruction from video data
Proceedings of the 6th International Conference on Computer Vision / Computer Graphics Collaboration Techniques and Applications
Hi-index | 0.00 |
NAT-IK, an interactive inverse-kinematics approach, robustly generates natural poses in a large human-reachable space. It employs adaptive kd clustering to select a representative frame set from a large motion database and employs sparse approximation to accelerate training and posing. Model training needs to be done only once. The training results contain 30 Mbytes of data, which can be imported conveniently into existing animation packages. The associated video shows a demonstration of NAT-IK.