Metaverse study

Computer vision (CV) and machine learning plays a big role in the development of Virtual Reality (VR) experiences for users. In the Metaverse, users often use VR devices such as headsets and motion capture devices to enhance the immersion of such digital spaces. However, computer vision and machi...

全面介紹

Saved in:
書目詳細資料
主要作者: Nguyen, Donvis
其他作者: Jun Zhao
格式: Final Year Project
語言:English
出版: Nanyang Technological University 2023
主題:
在線閱讀:https://hdl.handle.net/10356/166805
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
機構: Nanyang Technological University
語言: English
實物特徵
總結:Computer vision (CV) and machine learning plays a big role in the development of Virtual Reality (VR) experiences for users. In the Metaverse, users often use VR devices such as headsets and motion capture devices to enhance the immersion of such digital spaces. However, computer vision and machine learning are computationally intensive tasks given the amount of data required to be processed in real time. Given the limited computing power and battery life of wireless VR devices, these devices are inefficient in handling some of these tasks in real-time. However, with the development of mobileedge computing (MEC), it may serve as a solution to distribute computational resources across networks, to improve the data processing capability of the wireless VR headsets. In this paper, we explore a deep reinforcement learning algorithm to offload the computationally and resource-intensive tasks to MEC servers to reduce the latency and improve the performance of these VR devices, hoping to make connections and interactions to the Metaverse a better experience for users.