IEEE SECON2024
First-year Master's student Yui Maruyama presented research at IEEE SECON 2024
Publications & Talks
International Conference · 2024
Scalable and Distributed Optimization of Shared 3D Object Quality for Large-Scale Hybrid-Metaverses
Abstract
Hybrid-metaverses, integrating physical and virtual spaces, face a critical challenge in managing shared 3D object quality across multiple users with diverse preferences and limited network resources. This paper addresses the problem of allocating limited bandwidth for transmitting point cloud representations while maximizing overall user satisfaction. We propose a distributed optimization method that dynamically adjusts 3D object quality based on contextual importance, available resources, and user preferences. Our approach uses Input Convex Neural Networks (ICNN) to model user utility functions and employs the Alternating Direction Method of Multipliers (ADMM) for distributed optimization. Key advantages include scalability, adaptability, and improved quality of experience. Evaluation using open dataset demonstrates significant improvements in user satisfaction and resource utilization compared to baseline approaches. Our method achieves 93-94.6% accuracy in modeling user utility and shows up to 60% faster convergence for scenarios with 30 users, contributing to the balance between high-fidelity representation and efficient data management in hybrid-metaverses.
Research Note
Since the outbreak of COVID-19, the metaverse has gained attention as a tool for remote interaction. With the advancement of recent 3D sensing technologies, a new remote communication system is emerging that continuously scans the real world in 3D and shares it in virtual spaces. We have named this system "Hybrid Metaverse" and are conducting research aiming for its practical application.
The most critical challenge in realizing the hybrid metaverse is balancing the reduction of 3D video communication volume with maintaining video quality. To achieve this, it is necessary to solve an optimization problem that optimizes video quality under the constraint of limiting data capacity. In order to formulate this optimization problem, modeling video quality is essential. Since video quality is subjective to human perception, modeling it with simple formulas is challenging, and we employ neural networks for this purpose.
By utilizing neural networks for optimization, we are designing an algorithm that optimizes 3D video quality for multiple users under limited network resources, implementing and evaluating its performance. Moving forward, we plan to implement the entire hybrid metaverse system incorporating this optimization method.
Published Papers
- 丸山結, 天野辰哉, & 山口弘純. (2024). 実空間融合型メタバースにおける共有オブジェクト品質の分散型最適化手法. 研究報告コンピュータセキュリティ (CSEC), 2024(37), 1-8.
Related Lab Activities
Related Projects
新生活様式におけるコミュニティ形成のためのサイバーフィジカル空間共有基盤
National Institute of Information and Communications Technology (NICT) 高度通信・放送研究開発委託研究
ウイルス等感染症対策に資する情報通信技術の研究開発 課題C: アフターコロナ社会を形成するICT
