Evaluation of a Facial Animation Authoring Pipeline Seamlessly Supporting Performance Capture and Manual Key-pose Editing

Abstract

In this paper, we present an architecture following a novel animation authoring pipeline seamlessly supporting performance capture and manual editing of key-frames animation. This pipeline allows novice users to record and author sophisticated facial animations in a fraction of the time that would be required using traditional animation tools. This approach paves the way towards novel animation pipelines which seamlessly merge the roles of the animator and the actor. The second contribution is a method assessing a facial retargeting system, we conducted a user study where participants assessed the emotions conveyed by the facial expression displayed in the control and the authored animation. Contrary to existing evaluation methods, it factors out possible misinterpretations of the intended emotion and focuses on assessing the retargeting quality.