学术报告:Facial Modeling and Animation with Wrinkle Level Details

  目:Facial Modeling and Animation with Wrinkle Level Details

报告人:Zhigang Deng, Ph.D.




Dr. Zhigang Deng is Moores Professor and the Director of Graduate Studies in the Computer Science Department at University of Houston. He earned Ph.D. in Computer Science at the University of Southern California in 2006. Prior to that, he completed B.S. degree in Mathematics from Xiamen University, China, and M.S. in Computer Science from Peking University, China. His current research interests are in the broad areas of computer graphics, virtual human modeling & animation, human computer interaction, virtual/augmented reality, and computational surgery. He has published 170+ peer-reviewed research papers on various venues including TOG, SIGGRAPH, CHI, ICCV/ECCV, TVCG, ICRA, MICCAI, EG, SCA, etc. He is the recipient of many awards, including ACM ICMI Ten Year Technical Impact Award, UH Teaching Excellence Award, CASA Best Paper Award, IEEE TCCLS Best Paper Award, ICRA Best Medical Robotics Paper Award Runner-up, and Google Faculty Research Award. His research has been funded by NSF, NIH, NASA, DOD, QNRF, Texas NHARP, and various industry sources (including Electronic Arts, Honda, Google, etc). In addition to an Associate Editor for IEEE Transactions on Visualization and Computer Graphics, Computer Graphics Forum, etc., he has served as conference/program chairs for a number of renowned conferences including CASA 2014, SCA 2015, MIG 2022, PG 2023, and CGI 2024.Some of his research has been incorporated into mainstream graphics/animation packages such as Maya and Houdini, and has been practically used in many game studios including Electronic Arts. More information can be found on his webpage, http://graphics.cs.uh.edu/zdeng


Creation of fine-scale, realistic 3D facial models and animations for many applications, including films, virtual worlds, and games, has attracted a lot of attentions in recent years. Popular social media and mobile applications bring increasing demands for light-weight acquisition, animation, and manipulation of high fidelity face models on mobile devices. In this talk, I will present my recent efforts on realistic 3D face modeling and animation with wrinkle level details. First, I will present 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 this face modeling framework, I will further demonstrate its applications for real-time expression transformations in monocular face video and rea-time face swapping. Second, I will present an end-to-end system to automatically augment coarse-scale 3D faces with synthesized fine-scale geometric wrinkles. By formulating the wrinkle generation problem as a supervised generation task, we implicitly model the continuous space of face wrinkles via a compact generative model, such that plausible face wrinkles can be generated through effective sampling and interpolation in the space. Finally, I will also describe some other research efforts done by me in recent years.

Copyright(c) 2018 All Rights Reserved 版权所有:江西财经大学信息管理学院

地址:江西省南昌市昌北经济技术开发区玉屏大道 邮编:330032