Rendered Tile Reuse Scheme Based on FoV Prediction for MEC-Assisted Wireless VR Service

Liu, Chunyu; Wang, Kailin; Zhang, Heli; Li, Xi; Ji, Hong

doi:10.1109/tnse.2023.3234029

Cited by 10 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) Tiled Stream Approach: In tile-based streaming for VR video, the projected video in each frame is divided into tiles, as illustrated in Fig. 7 [90]. Each tile can be encoded, decoded, and rendered independently as separate video streams.…”

Section: B Streaming Approaches Of Vr Videosmentioning

confidence: 99%

“…The implementation of interactive real-time wireless VR applications with the low MTP delay and high QoE relies on fast rendering and transmission of mass data, which poses a huge challenge both to the computing power and transmission rate of existing mobile networks system [90], [129]- [132]. MEC brings the cloud computing facilities to the edge of networks through terminal, edge and fog computing infrastructure.…”

Section: A Multi-access Edge Computing (Mec)mentioning

confidence: 99%

“…Extensive research is being conducted in this regard, which is evident through a large number of emerging publications of using ML in VR systems. Deep RL (DRL)based ML techniques for FoV prediction in [182] and for QoE maximization in [183], recurrent neural network (RNN) based on long short-term memory (LSTM) architecture in [184] and gated recurrent unit (GRU) architecture for FoV predictionu in [90], [183], collective reinforcement learning (CRL) algorithm for allocate resources adaptively in [185], and meta-reinforcement learning (MRL) algorithm for access point (AP) selection and user association in [148], [186] are some of the recent works on the application of ML in VR networks.…”

Section: H Machine Learning (Ml)mentioning

confidence: 99%

See 2 more Smart Citations

A Survey on Virtual Reality over Wireless Networks: Fundamentals, QoE, Enabling Technologies, Research Trends and Open Issues

Hossain,

Jamalipour,

Munasinghe

2023

Preprint

View full text Add to dashboard Cite

<p>The purpose of this paper is to offer a comprehensive survey on the major technical issues and current research trends in supporting VR services over wireless networks. Additionally, the paper explores the fundamentals of VR technologies, applications, QoE requirements, spectrum requirements and key enabling technologies. Finally, a comprehensive discussion regarding potential research directions aimed at enhancing wireless VR experiences is also presented. Thus, this survey paper is structured to provide a strong baseline for the researchers working in wireless VR systems.</p>

show abstract

Section: B Streaming Approaches Of Vr Videosmentioning

confidence: 99%

Section: A Multi-access Edge Computing (Mec)mentioning

confidence: 99%

Section: H Machine Learning (Ml)mentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Virtual Reality over Wireless Networks: Fundamentals, QoE, Enabling Technologies, Research Trends and Open Issues

Hossain,

Jamalipour,

Munasinghe

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The deep reinforcement learning algorithm proposed by Zhang et al [21] studies the viewport prediction data rate requesting problems. The scheme proposed by Liu et al [22] reuses previously rendered tiles based on the prediction of the user's FoV, which leverages mobile edge computing to store and transmit the rendered tiles to the VR headset. The system presented by Jakob et al [23] uses millimeter-wave beamforming and exploits the spatial and temporal correlation of the user's head movement to predict the optimal beam direction and switch between beams quickly.…”

Section: Related Workmentioning

confidence: 99%

Federated Learning for Multi-view Synthesizing in Wireless Virtual Reality Networks

Guo

Qin

2022

2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)

View full text Add to dashboard Cite

The metaverse is expected to provide immersive entertainment, education, and business applications. However, virtual reality (VR) transmission over wireless networks is dataand computation-intensive, making it critical to introduce novel solutions that meet stringent quality-of-service requirements. With recent advances in edge intelligence and deep learning, we have developed a novel multi-view synthesizing framework that can efficiently provide computation, storage, and communication resources for wireless content delivery in the metaverse. We propose a three-dimensional (3D)-aware generative model that uses collections of single-view images. These single-view images are transmitted to a group of users with overlapping fields of view, which avoids massive content transmission compared to transmitting tiles or whole 3D models. We then present a federated learning approach to guarantee an efficient learning process.The training performance can be improved by characterizing the vertical and horizontal data samples with a large latent feature space, while low-latency communication can be achieved with a reduced number of transmitted parameters during federated learning. We also propose a federated transfer learning framework to enable fast domain adaptation to different target domains. Simulation results have demonstrated the effectiveness of our proposed federated multi-view synthesizing framework for VR content delivery.

show abstract

“…Each frame of VR video contains full view information, but the user can only see a small portion of the image within its FOV (field of view) when watching VR video, which means that there is a large amount of redundancy in each frame of VR image [11]. Ideally, only the valid image information within the user's FOV can be pushed based on the user's viewpoint information [12]. However, due to the limitations of network latency and bandwidth and the special nature of VR video viewing, this approach will lead to severe lag and image switching lag (switching images only when a new frame arrives) [13].…”

Section: Introductionmentioning

confidence: 99%

A Deep Reinforcement Learning-Based Optimal Computation Offloading Scheme for VR Video Transmission in Mobile Edge Networks

Xu,

Song

2023

IEEE Access

View full text Add to dashboard Cite

Large bandwidth, Low latency and intensive computing are the main challenge in high-performance virtual reality (VR) video transmission. As mobile edge computing (MEC) can provide computation and storage resources closer to terminals, it has been a promising mode in VR video transmission to substantially improve communication quality. This work focuses on the autonomous perception ability in MEC-supported VR video transmission, and introduces deep reinforcement learning to investigate optimal task offloading solutions. Therefore, this paper proposes a deep reinforcement learning-based optimal computation offloading scheme for VR video transmission in mobile edge networks. Specifically, a Deep Deterministic Policy Gradient-based computation offloading algorithm in designed as the main technical framework. The optimal planning of computation offloading strategies is viewed as a Markov decision problem, and a deep Q-Network is employed to deal with it. Finally, the setting of MEC-supported VR video transmission scenes is simulated, in which the proposed scheme is implemented for evaluation. The results are displayed in visualization format and show that the proposed task computation scheme can possess proper performance results in MEC-supported VR video transmission scenes.INDEX TERMS Virtual reality, video transmission, computation offloading, mobile edge networks, reinforcement learning.

show abstract

Rendered Tile Reuse Scheme Based on FoV Prediction for MEC-Assisted Wireless VR Service

Cited by 10 publications

References 35 publications

A Survey on Virtual Reality over Wireless Networks: Fundamentals, QoE, Enabling Technologies, Research Trends and Open Issues

A Survey on Virtual Reality over Wireless Networks: Fundamentals, QoE, Enabling Technologies, Research Trends and Open Issues

Federated Learning for Multi-view Synthesizing in Wireless Virtual Reality Networks

A Deep Reinforcement Learning-Based Optimal Computation Offloading Scheme for VR Video Transmission in Mobile Edge Networks

Contact Info

Product

Resources

About