Selected Readings in Vision and Graphics
Gregor A. Kalberer
Keywords: Character Modeling, Facial Animation, Visual Speech Synthesis, Appearance Based, ICA, PCA, Physiognomically Adapted Animation, Pseudo Muscles.
Modelierung virtueller Character, physiognomisch angepasste Gesichtsanimation, visuelle Sprachsynthese, PCA, ICA, statische Oberflächenanalyse, Pseudomuskeln.
Realistic face animation for speech is a real challenge, especially when we want to automate it to a large degree. This work proposes an efficient system for realistic speech animation. The system supports all steps of an entire animation pipeline, from the capture or design of 3D head models up to the synthesis and editing of the performance. This pipeline is fully 3D, which yields high flexibility in the use of the animated character. Real detailed 3D face dynamics, observed at video frame rate for thousands of points on the face of speaking actors, underpin the realism of the facial deformations. These are given a compact and intuitive representation via Independent Component Analysis. Performances amount to trajectories through Viseme Space. When asked to animate a face the system replicates the visemes that it has learned, and adds the necessary co-articulation effects. Realism has been improved through comparisons with motion captured groundtruth. Faces for which no 3D dynamics could be observed can be animated nonetheless. Their visemes are adapted automatically to their physiognomy by localizing the face in a Face Space.
About the author:
Gregor Arthur Kalberer studied Electrical Engineering with a minor in Communication Technology at the Swiss Federal Institute of Technology (ETH) Zürich, Switzerland, from which he received a Dipl. El. Ing. ETH in 1999. During his studies, he attended internships in the United States of America as well as in Belgium. In the year 1999, he joined the Computer Vision Institute at the ETH Zürich, where he investigated several problems in the field of facial animation. Within the scope of the ETH project VISEMES and the European project MESH, he was responsible for the analysis and synthesis of visual speech and for an entire animation pipeline, based on real facial dynamics. At the end of 2003, he finished his doctoral thesis and was awarded a Ph.D. degree (Dr. sc. techn.) from the ETH Zürich.
Reihe " Selected Readings in Vision and Graphics " im Hartung-Gorre Verlag
Direkt bestellen bei / to order directly from: Hartung.Gorre@t-online.de