Towards Immersive Metaverse with Semantic-Aware Wireless Networks
Abstract: Emerging with the support of computing and communications technologies, Metaverse is expected to bring users immersive service experiences over the entire virtual-reality spectrum. However, the stringent requirements of Metaverse services place a heavy demand on network resources in wireless, especially for services that are based on graphical extended reality and require rendering a plethora of virtual objects. To build a fully immersive Metaverse over wireless, it requires a radical paradigm shift of communication system from a passive transmission medium to a semantic-aware network where the semantics (meaning) of information are being understood and exploited before the transmission for network enhancement such as bandwidth saving and latency reduction. In this talk, I will share our recent works on applying semantic-aware techniques to design a personalized resource allocation scheme in order to sustain customized Metaverse services with greater Quality-of-Experience (QoE). Inspired by the human-centric features of the Metaverse, we first propose a novel metric named Meta-Immersion to model the QoE that incorporates both the objective KPIs and subjective feelings of Metaverse users. To capture the Metaverse service provision over wireless, we next study the interaction between the Metaverse service provider and the network infrastructure provider in the market, and provide an optimal contract design framework. Specifically, the utility of the Metaverse service provider, defined as a function of Metaverse users’ QoE, is to be maximized, while ensuring the incentives of the infrastructure provider. With the real datasets that we establish for Metaverse, we develop an attention-aware network resource allocation scheme that has two steps, i.e., attention prediction and QoE maximization. By using the predicted user attention (semantics), network resources such as the rendering capacity can be allocated optimally to maximize the QoE. The experimental results are then presented. Finally, I will provide an outlook of the promising research directions towards realizing an immersive Metaverse at the confluence of wireless, semantics, networking, and AI.
Bio: Zehui Xiong is currently an Assistant Professor at Singapore University of Technology and Design, and also an Honorary Adjunct Senior Research Scientist with Alibaba-NTU Singapore Joint Research Institute, Singapore. He received the PhD degree in Nanyang Technological University (NTU), Singapore. He was the visiting scholar at Princeton University and University of Waterloo. His research interests include wireless communications, Internet of Things, blockchain, edge intelligence, and Metaverse. He has published more than 200 research papers in leading journals and flagship conferences and many of them are ESI Highly Cited Papers. He has won over 10 Best Paper Awards in international conferences and is listed in the World’s Top 2% Scientists identified by Stanford University. He is now serving as the editor or guest editor for many leading journals including IEEE Journal on Selected Areas in Communications, IEEE Transactions on Vehicular Technology, IEEE Internet of Things Journal, IEEE Transactions on Cognitive Communications and Networking, and IEEE Transactions on Network Science and Engineering. He is the recipient of IEEE Early Career Researcher Award for Excellence in Scalable Computing, IEEE Technical Committee on Blockchain and Distributed Ledger Technologies Early Career Award, IEEE Internet Technical Committee Early Achievement Award, IEEE TCI Rising Star Award, IEEE Best Land Transportation Paper Award, IEEE CSIM Technical Committee Best Journal Paper Award, IEEE SPCC Technical Committee Best Paper Award, IEEE VTS Singapore Best Paper Award, Chinese Government Award for Outstanding Students Abroad, and NTU SCSE Best PhD Thesis Runner-Up Award.