GAMES Webinar 2022 – 220期(VR优化与应用：感知优化和个性化交互) | Shaoyu Chen (New York University)，Wanwan Li (George Mason University)
【GAMES Webinar 2022-220期】(VR&AR专题-VR优化与应用：感知优化和个性化交互)
报告嘉宾：Shaoyu Chen (New York University)
报告题目：Instant Reality: Gaze-Contingent Perceptual Optimization for 3D Virtual Reality Streaming
Media streaming has been adopted for a variety of applications such as entertainment, visualization, and design. Unlike video/audio streaming where the content is usually consumed sequentially, 3D applications such as gaming require streaming 3D assets to facilitate client-side interactions such as object manipulation and viewpoint movement. Compared to audio and video streaming, 3D streaming often requires larger data sizes and yet lower latency to ensure sufficient rendering quality, resolution, and latency for perceptual comfort. Thus, streaming 3D assets can be even more challenging than streaming audios/videos, and existing solutions often suffer from long loading time or limited quality.
To address this critical and timely issue, we propose a perceptually-optimized progressive 3D streaming method for spatial quality and temporal consistency in immersive interactions. Based on the human visual mechanisms in the frequency domain, our model selects and schedules the streaming dataset for optimal spatial-temporal quality. We also train a neural network for our model to accelerate this decision process for real-time client-server applications. We evaluate our method via subjective studies and objective analysis under varying network conditions (from 3G to 5G) and client devices (HMD and traditional displays), and demonstrate better visual quality and temporal consistency than alternative solutions.
Shaoyu Chen is a 5th year PhD student at New York University Tandon School of Engineering, supervised by Prof. Claudio T. Silva. His research interests include virtual reality, augmented reality and data visualization. Before joining NYU, he received his Bachelor of Engineering in Computer Science from Hong Kong University of Science and Technology.
报告嘉宾：Wanwan Li (George Mason University)
报告题目：Synthesizing Personalized Construction Safety Training Scenarios for VR Training
Construction industry has the largest number of preventable fatal injuries, providing effective safety training practices can play a significant role in reducing the number of fatalities. Building on recent advancements in virtual reality-based training, we devised a novel approach to synthesize construction safety training scenarios to train users on how to proficiently inspect the potential hazards on construction sites in virtual reality. Given the training specifications such as individual training preferences and target training time, we synthesize personalized VR training scenarios through an optimization approach. We validated our approach by conducting user studies where users went through our personalized guidance VR training, free exploration VR training, or slides training. Results suggest that personalized guidance VR training approach can more effectively improve users’ construction hazard inspection skills.
I am serving as a visiting assistant professor in the Dept. of Computer Science and Engineering at the University of South Florida (USF). I received my Ph.D. degree from the Department of Computer Science at George Mason University I used to work in the Design Computing and eXtended Reality (DCXR) Lab with Prof. Lap-Fai (Craig) Yu. I received an MS. (Master’s of Science) in Computer Science major from the University of Central Florida and a BE (Bachelor of Engineer) in computer science and technology major from the Harbin Institute of Technology(HIT).
My research interests include Computer Graphics (CG), Virtual Reality (VR), Augmented Reality (AR), Augmented Virtuality (AV), Edutainment & e-Training, Procedural Modeling, Computational Design, Deep Learning (DL), Sketch-Based Interface (SBI), Brain-Computer Interface (BCI). Here is my Portfolio. Besides enjoying computer programming, I am also interested in oil painting, piano music composing and cello performance.
肖双九，上海交通大学软件学院副教授，博士，硕士生导师。中国图学学会图学学课发展工作委员会副主任，中国计算机学会会员，中国人工智能学会智能 CAD 与数字艺术专业委员。
研究领域包括计算机图形动画、数字孪生、虚拟现实、增强现实、智能人机交互技术等。在三维模型重建、实时渲染、骨骼动画、VR/AR方面有很多的技术积累和项目成果。作为项目负责人完成了国家自然科学基金项目，国家 863 项目、省部委项目及国际合作等多项课题的研究。所负责的《三维实境仿真训练系统》曾获得全军科技进步一等奖。在本研究领域的多种国际学术会议和国家一级核心期刊上发表学术论文 100 余篇。
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；