A Motion Style Toolbox

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9238)

Abstract

We present a Matlab toolbox for synthesis and visualization of human motion style. The aim is to support development of expressive virtual characters by providing implementations of several style related motion synthesis methods thus allowing side-by-side comparisons. The implemented methods are based on recorded (captured or synthetic) motions, and include linear motion interpolation and extrapolation, style transfer, rotation swapping per body part and per quaternion channel, frequency band scaling and swapping, and Principal/Independent Component Analysis (PCA/ICA) based synthesis and component swapping.

Keywords

Computer animation Human motion Motion style Motion synthesis Toolbox 

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Computer ScienceAalto UniversityEspoo Finland

Personalised recommendations