Fine-Scale Facial-Animation Capture, Generation, and Manipulation

The Seminar with Dr. Zhigang Deng has been cancelled.

When: Monday, March 16, 2020
Where: PGH 232
Time: 11:00 AM

CANCELLED

Speaker: Dr. Zhigang Deng, University of Houston

Host: Dr. Thamar Solorio

Creation of fine-scale 3D facial models and realistic facial animations for applications, including films, VR systems, and games, have attracted a lot of attention in recent years. Popular social media and mobile applications bring increasing demand for light-weight acquisition and manipulation of high-resolution facial performances on mobile devices. In this talk, I will present several of our recent works on monocular video, fine-scale facial-animation capture, generation, and manipulation. The first work I will present is a novel real-time framework to reconstruct high-resolution facial geometry and appearance by capturing an individual-specific face model with fine-scale wrinkle details from a single monocular RGB video input. On top of the first work, I will further present a deep learning-based method to automatically augment any coarse-scale 3D faces with synthesized fine-scale geometric wrinkles. Finally, I will present a real-time and automated method to replace a face in a target video clip from a single source portrait image.

Bio:

Dr. Zhigang Deng is a Full Professor of Computer Science at the University of Houston and the Director of Graduate Studies at UH's Computer Science Department. He earned his Ph.D. in Computer Science at the University of Southern California in 2006. He also completed a B.S. degree in Mathematics from Xiamen University (China), and a M.S. in Computer Science from Peking University (China). His current research interests are in the broad areas of computer graphics/animation, virtual human modeling & animation, human computer interaction, and humanoid robots. He has published more than 137 peer-reviewed research papers including 36 ACM/IEEE Transactions and journal papers, and many papers on prestigious conferences including SIGGRAPH, CHI, ICCV, MICCAI, EG, I3D, SCA, ICRA, etc. His Google scholar citations are more than 4350 (as of Feb 18, 2020). He is the recipient of many awards including CASA Best Paper Award or runner-up (2017 & 2018), ACM ICMI Ten-Year Technical Impact Award (2014), UH Teaching Excellence Award (2013), NSFC Overseas and Hong Kong/Macau Young Scholars Collaborative Research Award (2013), ICRA Best Medical Robotics Paper Award Runner-up (2012), and Google Faculty Research Award (2010). His research has been funded by NSF, NIH, NASA, DOD, QNRF, Texas NHARP, and various industry sources (including EA, Honda, Google, Nokia, NVidia, etc). His research on SSDR has been widely incorporated into mainstream graphics/animation packages including Maya and Houdini, as well as being used in many game studios such as Electronic Arts and Naughty Dog. More information can be found on his webpage, http://graphics.cs.uh.edu/zdeng.