Sciweavers

123 search results - page 2 / 25
» Synthesize stylistic human motion from examples
Sort
View
CVPR
2006
IEEE
15 years 26 days ago
3D People Tracking with Gaussian Process Dynamical Models
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...
Raquel Urtasun, David J. Fleet, Pascal Fua
ICDE
2005
IEEE
157views Database» more  ICDE 2005»
15 years 6 days ago
MoDB: Database System for Synthesizing Human Motion
Enacting and capturing real motion for all potential scenarios is terribly expensive; hence, there is a great demand to synthetically generate realistic human motion. However, it ...
Timothy Edmunds, S. Muthukrishnan, Subarna Sadhukh...
HUMO
2000
Springer
14 years 2 months ago
Realistic Synthesis of Novel Human Movements from a Database of Motion Capture Examples
In this paper we present a system that can synthesise novel motion sequences from a database of motion capture examples. This is achieved through learning a statistical model from...
L. M. Tanco, Adrian Hilton
TVCG
2010
208views more  TVCG 2010»
13 years 9 months ago
Example-Based Human Motion Denoising
—With the proliferation of motion capture data, interest in removing noise and outliers from motion capture data has increased. In this paper, we introduce an efficient human mo...
Hui Lou, Jinxiang Chai
SIGGRAPH
2000
ACM
14 years 3 months ago
Style machines
We approach the problem of stylistic motion synthesis by learning motion patterns from a highly varied set of motion capture sequences. Each sequence may have a distinct choreogra...
Matthew Brand, Aaron Hertzmann