Title :
Personalised real-time idle motion synthesis
Author :
Egges, Arjan ; Molet, Tom ; Magnenat-Thalmann, Nadia
Author_Institution :
MIRALab, Geneva Univ., Switzerland
Abstract :
In this paper, we propose an animation approach based on principal component analysis that allows generating two layers of subtle motions: small posture variations and personalised change of balance. Such a motion generator is needed in many cases when one attempts to create an animation sequence out of a set of existing clips. In nature there exists no motionless character, while in computer animation we often encounter cases where no planned actions, such as waiting for another actor finishing his/her part, is implemented as a stop/frozen animation. We identify many situations where a flexible idle motion generator can help: from synchronisation of speech/body animation duration, to dynamic creation of stand still variations in between two active plays. Our approach overcomes the limitations of using a small set of existing clips as a basis for synthesizing idle motions, such as unnatural repetition of movements and difficulties to insert idle motions into an animation without breaking its continuity. A realistic animation is obtained by blending small posture variations with personalised balance shifting animations.
Keywords :
computer animation; image motion analysis; principal component analysis; real-time systems; computer animation; idle motion generation; personalised balance shifting animations; personalised real-time idle motion synthesis; principal component analysis; small posture variations; Animation; Fatigue; Finishing; Humans; Joints; Motion analysis; Motor drives; Muscles; Principal component analysis; Speech synthesis;
Conference_Titel :
Computer Graphics and Applications, 2004. PG 2004. Proceedings. 12th Pacific Conference on
Print_ISBN :
0-7695-2234-3
DOI :
10.1109/PCCGA.2004.1348342