Motion editing with spacetime constraints
Proceedings of the 1997 symposium on Interactive 3D graphics
Retargetting motion to new characters
Proceedings of the 25th annual conference on Computer graphics and interactive techniques
Nonlinear component analysis as a kernel eigenvalue problem
Neural Computation
Physically based motion transformation
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
A hierarchical approach to interactive motion editing for human-like figures
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
SIGGRAPH '88 Proceedings of the 15th annual conference on Computer graphics and interactive techniques
Synthesis of complex dynamic character motion from simple animations
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Automated Derivation of Primitives for Movement Classification
Autonomous Robots
View-Invariant Representation and Recognition of Actions
International Journal of Computer Vision
Human Activity Recognition Using Multidimensional Indexing
IEEE Transactions on Pattern Analysis and Machine Intelligence
Motion synthesis from annotations
ACM SIGGRAPH 2003 Papers
Efficient synthesis of physically valid human motion
ACM SIGGRAPH 2003 Papers
Style-based inverse kinematics
ACM SIGGRAPH 2004 Papers
A physically-based motion retargeting filter
ACM Transactions on Graphics (TOG)
Adaptation of performed ballistic motion
ACM Transactions on Graphics (TOG)
Learning physics-based motion style with nonlinear inverse optimization
ACM SIGGRAPH 2005 Papers
Estimating the Support of a High-Dimensional Distribution
Neural Computation
| Hi-index | 0.00 |
This paper presents a computational model of stylistic similarity between human motions that is statistically derived from a comprehensive collection of captured, stylistically similar motion pairs. In this model, a set of hypersurfaces learned by single-class SVM and kernel PCA characterize the region occupied by stylistically similar motion pairs in the space of all possible pairs. The proposed model is further applied to a system for adapting an existing clip of human motion to a new environment, where stylistic distortion is avoided by enforcing stylistic similarity of the synthesized motion to the existing motion. The effectiveness of the system has been verified by 18 distinct adaptations, which produced walking, jumping, and running motions that exhibit the intended styles as well as the intended contact configurations.