Detection of inconsistency between shape and motion in realistic female and male animation

Abstract

Capturing the motion of a person and retargeting it to a virtual character with a different body shape is common practice in computer animation. This inconsistency between motion and shape often makes animations look unrealistic. It remains unclear which aspects of an animation affect how realistic it is perceived. Previous research has found detection of the inconsistency between motion and shape in biometric virtual characters to be at chance level for actions that involve object manipulation. Here, we test whether similar results are obtained for actions not involving objects and compare the detection of inconsistency in realistic female and male animation for actions with and without object manipulation. For creating our stimuli, we used the animations of five pairs of female and male performers with large differences in body weight from the bmlRUB database when throwing a ball, lifting a box, jumping, and walking. For each actor pair, we created inconsistent animations by combining the body shape from one actor with the motion from the other actor. For the consistent stimuli, the body shape and motion came from the same actor. In each trial of the experiment, participants observed one consistent and one inconsistent animation and selected which of the two they perceived to be inconsistent. Our results showed that for both female and male animations, participants’ detection rate was above chance for walking, and was at chance level for throwing. For lifting and jumping, the detection rate was at chance level for female animations and above chance level for male animations. Overall, detection rate was low which is promising news for realistic human animations but tended to be higher for male animations. Future research should investigate a broader range of actions to determine which are perceptually most affected by motion retargeting.