Avatars and Faces

Summary: In this paper, we propose a technique that reconstructs 3D shapes and motions of eyelids in real time. Combining with the tracked face and eyeballs, our system generates full face results with more detailed eye regions. Our technique is applicable for different human races, eyelid shapes and motions.

Author(s): Quan Wen, Software School, Tsinghua University
Feng Xu, Software School, Tsinghua University
Ming Lu, Tsinghua University
Jun-Hai Yong, Software School, Tsinghua University

Speaker(s): Quan Wen, Tsinghua University

Summary: We learn a model of head shape, pose, and expression that is compact, easy to fit to data, and is much more expressive, realistic, and general than existing models of the same complexity. We train the model from thousands of people and 4D sequences and make it available for research.

Author(s): Tianye Li, Max Planck Institute for Intelligent Systems, University of Southern California
Timo Bolkart, Max Planck Institute for Intelligent Systems
Michael J. Black, Max Planck Institute for Intelligent Systems
Hao Li, Pinscreen, USC Institute for Creative Technologies, University of Southern California
Javier Romero, Max Planck Institute for Intelligent Systems, Body Labs

Speaker(s): Tianye Li, University of Southern California and Max Planck Institute for Intelligent Systems

Summary: We present a fully automatic framework that digitizes a complete 3D head with hair from a single unconstrained image. While the generated face is a high-quality textured mesh, we propose a versatile and efficient polygonal strips (polystrips) representation for the hair, compatible with existing real-time game engines.

Author(s): Liwen Hu, Pinscreen, University of Southern California
Shunsuke Saito, Pinscreen, University of Southern California
Lingyu Wei, University of Southern California, Pinscreen
Koki Nagano, Pinscreen
Jens Fursund, Pinscreen
Iman Sadeghi, Pinscreen
Jaewoo Seo, Pinscreen
Yen-Chun Chen, Pinscreen
Hao Li, USC Institute for Creative Technologies, Pinscreen, University of Southern California

Speaker(s): Liwen Hu, Pinscreen, University of Southern California

Summary: We present a technique to automatically animate a still portrait, making it possible for the subject in the photo to come to life and express various emotions.

Author(s): Hadar Averbuch-Elor, Tel Aviv University
Daniel Cohen-Or, Tel Aviv University
Johannes Kopf, Facebook
Michael Cohen, Facebook

Speaker(s): Hadar Averbuch-Elor, Tel-Aviv University