Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Interactive motion generation from examples
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Interactive control of avatars animated with human motion data
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Motion capture assisted animation: texturing and synthesis
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Implicit Probabilistic Models of Human Motion for Synthesis and Tracking
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
An evaluation of a cost metric for selecting transitions between motion segments
Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation
Layered acting for character animation
ACM SIGGRAPH 2003 Papers
Precomputing avatar behavior from human motion data
SCA '04 Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation
Controllable real-time locomotion using mobility maps
GI '05 Proceedings of Graphics Interface 2005
Search and transitioning for motion captured sequences
Proceedings of the ACM symposium on Virtual reality software and technology
Precomputing avatar behavior from human motion data
Graphical Models - Special issue on SCA 2004
Automatic splicing for hand and body animations
Proceedings of the 2006 ACM SIGGRAPH/Eurographics symposium on Computer animation
ACM SIGGRAPH 2008 classes
Modeling spatial and temporal variation in motion data
ACM SIGGRAPH Asia 2009 papers
Representing cyclic human motion using functional analysis
Image and Vision Computing
Modeling style and variation in human motion
Proceedings of the 2010 ACM SIGGRAPH/Eurographics Symposium on Computer Animation
One-to-many: example-based mesh animation synthesis
Proceedings of the 12th ACM SIGGRAPH/Eurographics Symposium on Computer Animation
Hi-index | 0.00 |
In this paper, we describe a method for synthesizing joint angle and translation data based on the information in motion capture data. The synthetic data is realistic not only in that it resembles the original training data, but also in that it has random variations that are statistically similar to what one would find in repeated measurements of the motion. To achieve this result, the training data is broken into frequency bands using wavelet decomposition, and the information in these bands is used to create the synthetic data one frequency band at a time. The method takes into account the fact that there are correlations among numerous features of the data. For example, a point characterized by a particular time and frequency band will depend upon points close to it in time in other frequency bands. Such correlations are modeled with a kernel-based representation of the joint probability distributions of the features. Sampling from these densities and improving the results using a new iterative maximization technique synthesize the data. We have applied this technique to the synthesis of joint angle and translation data of a wallaby hopping on a treadmill. The synthetic data was used to animate characters that have limbs proportional to the wallaby.