Wednesday, 10 August 2:00 pm - 3:30 pm | East Building, Exhibit Hall A
Session Chair: Miquel A. Otaduy, Universidad Rey Juan Carlos
Leveraging Motion Capture and 3D Scanning for High-Fidelity Facial Performance Acquisition
This new approach for acquiring high-fidelity 3D facial performances with realistic dynamic wrinkles and fine facial details leverages state-of-the-art motion capture technology and advanced 3D scanning technology of facial-performance acquisition.
Haoda Huang
Microsoft Research Asia
Jinxiang Chai
Texas A&M University
Xin Tong
Microsoft Research Asia
Hsiang-Tao Wu
Microsoft Research Asia
High-Quality Passive Facial Performance Capture Using Anchor Frames
A new technique for high-quality facial performance capture that leverages the repetitive structure of face motions to automatically locate frames with similar expressions, called anchor frames. High-resolution geometry is reconstructed and temporal motion is propagated in parallel using robust image-space matching between the anchor frames.
Thabo Beeler
ETH Zürich and Disney Research Zürich
Fabian Hahn
Disney Research Zürich
Derek Bradley
Disney Research Zürich
Bernd Bickel
Disney Research Zürich
Paul Beardsley
Disney Research Zürich
Craig Gotsman
Technion-Israel Institute of Technology
Robert W. Sumner
Disney Research Zürich
Markus Gross
Disney Research Zürich
Interactive Region-Based Linear 3D Face Models
A linear face modelling approach that generalizes better to unseen data and allows click-and-drag interaction for animation. The model consists of a collection of linear submodels independently trained but related through shared boundaries. It is demonstrated on dense-face motion capture data.
J. Rafael Tena
Disney Research Pittsburgh
Fernando De la Torre
Carnegie Mellon University
Iain Matthews
Disney Research Pittsburgh
Real-Time Performance-Based Facial Animation
This paper presents a system for performance-based character animation that enables any user to control the facial expressions of a digital avatar in real-time using a non-intrusive, commercially available 3D sensor.
Thibaut Weise
École Polytechnique Fédérale de Lausanne
Sofien Bouaziz
École Polytechnique Fédérale de Lausanne
Hao Li
École Polytechnique Fédérale de Lausanne
Mark Pauly
École Polytechnique Fédérale de Lausanne