Technical Papers

    Avatars

    Thursday, 21 November

    11:00 - 12:45

    Room S224 + S225

    Designing and Fabricating Mechanical Automata from Mocap Sequences

    We present an automatic method that takes a motion sequence of a humanoid character and generates the design for a mechanical figure that approximates the input motion when driven by a single constant-speed crank.


    Duygu Ceylan, Ecole Polytechnique Federale de Lausanne
    Wilmot Li, Adobe Research
    Niloy Mitra, University College London
    Maneesh Agrawala, University of California Berkeley
    Mark Pauly, Ecole Polytechnique Federale de Lausanne

    3D Self-Portraits

    With our system any ordinary user can capture complete and fully textured 3D models of themselves in minutes, using only a single Kinect sensor, in the uncontrolled lighting environment of their own home.


    Hao Li, University of Southern California
    Etienne Vouga, Columbia University
    Anton Gudym, Artec Group Inc.
    Linjie Luo, Adobe Research
    Jonathan Barron, University of California, Berkeley
    Gleb Gusev, Artec Group, Inc.

    Anatomy Transfer

    We propose the first semi-automatic method for creating anatomical structures, such as bones, muscles, viscera and fat tissues by
    transferring a reference anatomical model from an input template
    to an arbitrary target character, only defined by its boundary representation
    (skin)


    Dicko Ali-Hamadi, Institute National de Recherche en Informatique et en Automatique
    Tiantian Liu, University of Pennsylvania
    Benjamin Gilles, Centre National de la Recherche Scientifique
    Ladislav Kavan, University Of Pennsylvania
    Francois Faure, Institute National de Recherche en Informatique et en Automatique
    Marie-Paule Cani, Institute National de Recherche en Informatique et en Automatique Rhone-Alpes - Grenoble Universities

    Augmenting Physical Avatars using Projector-Based Illumination

    Animated animatronic figures are a unique way to give physical presence to a character. We present a complete process for augmenting physical avatars using projector-based illumination, significantly increasing their expressiveness. The result is a highly expressive avatar that features facial details and motion otherwise unattainable due to physical constraints.


    Amit Bermano, Disney Research Zurich / Eidgenoessische Technische Hochschule Zurich
    Philipp Brüschweiler, Disney Research Zurich / Eidgenoessische Technische Hochschule Zurich
    Anselm Grundhöfer, Disney Research Zurich
    Daisuke Iwai, Osaka University
    Bernd Bickel, Disney Research Zurich
    Markus Gross, Disney Research Zurich / Eidgenoessische Technische Hochschule Zurich