Skip to Main content Skip to Navigation
Conference papers

A Framework for Scalable Virtual Worlds Using Spatially Organized P2P Networks

Romain Cavagna 1, 2, * Maha Abdallah 1 Eliya Buyukkaya 1 Christian Bouville 3
* Corresponding author
1 MALIRE - Machine Learning and Information Retrieval
LIP6 - Laboratoire d'Informatique de Paris 6
3 BUNRAKU - Perception, decision and action of real and virtual humans in virtual environments and impact on real environments
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, ENS Cachan - École normale supérieure - Cachan, Inria Rennes – Bretagne Atlantique
Abstract : The general craze for virtual environments, the potential of augmented reality applications and the announced revolution of the Internet world (Web 2.0, Web 3D.0) are key points for the emergence of an 'ambient' Web which will make it possible for users to communicate, collaborate, entertain, work and exchange content. In this context, content storage, delivery, and reproduction are among the essential points for the deployment of a highly scalable platform of wide reality. In this paper, we propose a self-scalable peerto- peer architecture for the navigation in network-based virtual worlds. To reach this goal, we propose a fully distributed and adaptive streaming method that quickly adapts the reproduced content according to user interaction. Our content delivery strategy has been implemented and tested on a dedicated simulator with a large 3D city model. The presented results show the efficiency of our strategy in very critical conditions.
Complete list of metadatas
Contributor : Bouville Christian <>
Submitted on : Saturday, May 1, 2010 - 7:12:12 PM
Last modification on : Friday, July 10, 2020 - 4:00:23 PM



Romain Cavagna, Maha Abdallah, Eliya Buyukkaya, Christian Bouville. A Framework for Scalable Virtual Worlds Using Spatially Organized P2P Networks. The 14th IEEE International Conference on Parallel and Distributed Systems (ICPADS'08), Dec 2008, Melbourne, Australia. pp.853-858, ⟨10.1109/ICPADS.2008.125⟩. ⟨inria-00479677⟩



Record views