Natural Character Posing from a Large Motion Database

Authors:
Xiaomao Wu;Maxime Tournier;Lionel Reveret
Affiliations:
Crytek;INRIA;INRIA
Venue:
IEEE Computer Graphics and Applications
Year:
2011

Citing 0
Cited 2

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
Classification and translation of style and affect in human motion using RBF neural networks

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.