Abstract:

We present NAT-IK, a new interactive inverse kinematics scheme that can robustly and interactively generate natural poses in a large human-reachable space. NAT-IK employs an adaptive kd-clustering algorithm to select a representative frame set from a large motion database, and a sparse approximation algorithm to accelerate the training and posing speeds. The model training process needs
to be done only once. The training results contain 30MB of data, which can be conveniently imported into existing animation  packages.

References:

 Xiaomao Wu, Maxime Tournier and Lionel Reveret. Natural character posing from a large motion database. To appear in IEEE Computer Graphics and Applications.

Xiaomao Wu, Lionel Reveret and Maxime Tournier. Interactive character posing from large motion database. ACM SIGGRAPH / Eurographics Symposium on Computer Animation Poster Proceedings, pp: 1-2, 2008.

Paper [PDF, 734 KB]

Tech Report [Coming soon]

Video [AVI, 19.9 MB]