REU Site: Research Experience for Undergraduates in Immersive Media Computing

该项目建立了一个新的本科生研究体验(REU)网站，由佐治亚州立大学计算机科学系和创意媒体产业研究所联合主办。每年夏天，全国各地的本科生将与一群经验丰富的教职员工合作，开展沉浸式媒体计算的尖端研究。沉浸式媒体计算是一种新兴的计算范式，旨在在真实或虚拟的环境中创造3D沉浸感。沉浸式媒体计算最近的发展使一系列引人注目的技术成为可能，如360度视频、增强现实和虚拟现实，潜在地改变了医疗、培训、教育、娱乐、旅游等领域的广泛领域。REU网站将培训本科生学习这种新兴的计算模式，并有利于他们的研究生申请和找工作。通过研讨会、演示、演讲、实地考察等各种活动，本科生也将提升自己的专业技能。该REU网站旨在扩大代表不足的群体对研究活动的参与，特别是在历史上有许多黑人学院和女子学院的邻近地区。沉浸式媒体计算的新兴性质导致了该项目强大的智力价值。尽管对常规图像和视频的研究有着丰富的历史，但沉浸式内容的计算带来了巨大的研究挑战。将开发新的算法来解决端到端沉浸式媒体计算系统中的五个研究问题：(1)沉浸式内容必须被压缩以减少传输的数据量，同时保持内容的保真度；(2)压缩的沉浸式内容需要以带宽高效的方式被流传送到远程显示器；(3)接收的沉浸式内容应该基于用户头部方向在CPU/GPU中使用并行计算来快速呈现；(4)原始沉浸式内容必须被进一步分析以提取感兴趣的事件；以及(5)需要在沉浸式内容上覆盖附加信息以增强沉浸式可视化体验。除了算法和模型设计，还将建立真实世界的系统来证明研究的有效性。这一奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This project establishes a new Research Experiences for Undergraduates (REU) Site that is jointly hosted by the Department of Computer Science and the Creative Media Industries Institute at Georgia State University. Undergraduate students across the nation will work with a group of experienced faculty members and conduct cutting-edge research in immersive media computing during each summer. Immersive media computing is an emerging computing paradigm that aims to create the sensation of 3D immersion in a real or virtual environment. The recent development of immersive media computing has enabled a host of compelling technologies such as 360-degree videos, Augmented Reality, and Virtual Reality, potentially transforming a wide spectrum of sectors in healthcare, training, education, entertainment, tourism, etc. The REU site will train undergraduate students in this emerging computing paradigm and benefit their graduate application and job hunting. Through various activities such as seminars, demos, presentations, field trips, and other professional development opportunities, undergraduate students will also enhance their professional skills. This REU site aims to broaden the participation of underrepresented groups in research activities, especially in the neighboring regions with numerous Historically Black Colleges and Universities and Women Colleges. The emerging nature of immersive media computing leads to the strong intellectual merit of this project. Despite the rich history of research on regular images and videos, the computing of immersive content poses significant research challenges. New algorithms will be developed to address five research problems across the end-to-end immersive media computing system: (1) immersive content must be compressed to reduce the amount of data transported while maintaining the fidelity of the content; (2) the compressed immersive content needs to be streamed to the remote display in a bandwidth-efficient way; (3) the received immersive content should be quickly rendered based on the user head orientation using parallel computing in CPUs/GPUs; (4) the raw immersive content must be further analyzed to extract the events of interest; and (5) additional information needs to be overlaid over the immersive content to enhance the immersive visualization experience. In addition to algorithm and model designs, real-world systems will be built to demonstrate the effectiveness of the research.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.