Automatically Generating Eye Motion in Virtual Agents

Eye Motion has a fundamental role in verbal and non-verbal communication among people. It can express emotions and regulate the flow of conversation. For this reason, it is very important that these movements can be realistic in Computer Animation’s applications, such as virtual humans in general and game/movies characters. This paper presents a model for producing eye movements in synthetic agents. The main goal is to improve the realism of facial animation of such agents during conversational interactions. The contribution of this work is the inclusion of saccade behaviours in eyes motion, correlated with emotional attributes and also dependent of agents’ role during interaction, e.g. if agent is listening or talking. We investigate the impact of face animations in human-computer interactions by including saccade motions, emotional attributes and role’s dependent animation. The experimental results indicate that increasing details in eyes animation can significantly improve the realism of facial animation.