GAMES Webinar 2019 – 113期（Geometric Deep Learning 专题进展报告） | Hao Li (USC)

【GAMES Webinar 2019-113期】

主持人：黄其兴，德克萨斯大学奥斯汀分校（个人主页：http://www.cs.utexas.edu/~huangqx/）

报告嘉宾：Hao Li，University of Southern California

报告时间：2019年10月11日 上午10:00-11:30（北京时间）

报告题目：AI-DRIVEN HUMAN AND CONTENT DIGITIZATION

报告摘要：

My presentation will motivate the importance of digital humans in our society and highlight use cases in fashion, simulation, and AR/VR. I will then present various deep learning techniques that we have developed at Pinscreen and USC/ICT that facilitate the digitization of photorealistic humans at scale without the need of conventional production studios. I will present some new research from Pinscreen for robust avatar creation from highly unconstrained input images, and talk about our real-time facial expression synthesis framework paGAN. Going beyond the facial domain, I will present our recent work at USC/ICT on full body avatar digitization where fully clothed 3D human shapes can be inferred from as little as a single input photograph, and explain how general object (inter-class) digitization can be facilitated using truly differentiable rendering frameworks, such as our work on soft rasterization. This presentation will open up the question in whether we are converging toward an AI-driven universal content generator which could pose significant challenges to privacy and the spread of disinformation.

讲者简介：

Hao Li is CEO/Co-Founder of Pinscreen, Associate Professor of Computer Science at the University of Southern California, and the director of the Vision and Graphics Lab at the USC Institute for Creative Technologies. Hao’s work in Computer Graphics and Computer Vision focuses on digitizing humans and capturing their performances for immersive communication and telepresence in virtual worlds. His research involves the development of novel geometry processing, data-driven, and deep learning algorithms. He is known for his seminal work in non-rigid shape alignment, real-time facial performance capture, hair digitization, and dynamic full body capture. He was previously a visiting professor at Weta Digital, a research lead at Industrial Light & Magic / Lucasfilm, and a postdoctoral fellow at Columbia and Princeton Universities. He was named top 35 innovator under 35 by MIT Technology Review in 2013 and was also awarded the Google Faculty Award, the Okawa Foundation Research Grant, as well as the Andrew and Erna Viterbi Early Career Chair. He won the Office of Naval Research (ONR) Young Investigator Award in 2018 and was named named to the DARPA ISAT Study Group in 2019. Hao obtained his PhD at ETH Zurich and his MSc at the University of Karlsruhe (TH).

讲者个人主页：http://www.hao-li.com/Hao_Li/Hao_Li_-_about_me.html

GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播？”及“如何加入GAMES微信群？”的信息；
GAMES主页的“资源分享”有往届的直播讲座的视频及PPT等。
观看直播的链接：http://webinar.games-cn.org