講題：AI-Assisted Efficient Streaming of 3D Gaussian Splatting Scenes: From Static to Dynamic Content

Time: 5/14(Wed) 15:30-17:20

Location: ED117

Speaker:       

Prof. Cheng-Hsin Hsu/Dept. of Computer Science, National Tsing Hua University

【講題大綱    】

This talk presents recent research from my Ambient Intelligence for Immersive Networked Systems (AIINS) Lab at NTHU, focused on efficient and adaptive delivery of immersive 3D content. We explore AI-assisted techniques for both dynamic 3D Gaussian Splatting (3DGS) and point cloud representations. Our work traces a trajectory from optimizing the streaming of static 3DGS scenes, through adaptive delivery of dynamic 3DGS content, to a novel paradigm for motion estimation of dynamic point clouds for mobile devices that cannot afford 3DGS rendering.

【講者經歷】

Cheng-Hsin Hsu received M.S./B.S. degrees from National Chung-Cheng University, an M.Eng. degree from the University of Maryland, and a Ph.D. degree from Simon Fraser University. He joined the Department of Computer Science at National Tsing Hua University in 2011. He was promoted to full Professor in 2021. Before accepting the teaching position, he was with the Deutsche Telekom Laboratory (California), Motorola Inc. (Illinois), and Lucent Technologies (Maryland) for more than six years. Cheng-Hsin has been a Visiting Scholar with the University of California Irvine (Summer 2013), the Qatar Computing Research Institute (Summer 2014), the University of Illinois Urbana-Champaign (Spring 2016), and the University of California Irvine (Fall 2018 and Spring 2019).

Cheng-Hsin’s research interests lie in multimedia networking, immersive videos, Internet-of-Things (IoT), smart cities, digital twins, and computer networks.