dc.contributor.author | Lewis, Ryan Hardesty | |
dc.date.accessioned | 2025-09-11T19:36:19Z | |
dc.date.available | 2025-09-11T19:36:19Z | |
dc.date.issued | 2025-08-10 | |
dc.identifier.isbn | 979-8-4007-1550-1 | |
dc.identifier.uri | https://hdl.handle.net/1721.1/162646 | |
dc.description | SIGGRAPH Labs ’25, Vancouver, BC, Canada | en_US |
dc.description.abstract | MeshTorrent is a peer-to-peer platform for automated 3D content creation and exchange, inspired by BitTorrent-style file sharing. By merging AI-based text-to-3D generation with swarm-based distribution, MeshTorrent harnesses the combined bandwidth and storage resources of its users, enabling scalable and decentralized sharing of 3D assets. This paper describes the core design of MeshTorrent, including an AI workflow for generating fresh .glb files, metadata management via a distributed hash table, partial previews for quick inspection, and specialized extensions for 2D sprites (SpriteTorrent) and rigged character models (RigTorrent). Preliminary tests show faster content download times than single-host alternatives, reduced server costs, and robust resilience to network churn, advancing an open ecosystem for collaborative 3D model exchange. | en_US |
dc.publisher | ACM|Special Interest Group on Computer Graphics and Interactive Techniques Conference Labs | en_US |
dc.relation.isversionof | https://doi.org/10.1145/3721251.3736272 | en_US |
dc.rights | Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. | en_US |
dc.source | Association for Computing Machinery | en_US |
dc.title | MeshTorrent: A Community-Driven P2P System for AI-Generated 3D Model Creation and Distribution | en_US |
dc.type | Article | en_US |
dc.identifier.citation | Ryan Hardesty Lewis. 2025. MeshTorrent: A Community-Driven P2P System for AI-Generated 3D Model Creation and Distribution. In Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Labs (SIGGRAPH Labs '25). Association for Computing Machinery, New York, NY, USA, Article 8, 1–2. | en_US |
dc.contributor.department | MIT Institute for Data, Systems, and Society | en_US |
dc.identifier.mitlicense | PUBLISHER_POLICY | |
dc.eprint.version | Final published version | en_US |
dc.type.uri | http://purl.org/eprint/type/ConferencePaper | en_US |
eprint.status | http://purl.org/eprint/status/NonPeerReviewed | en_US |
dc.date.updated | 2025-09-01T07:55:09Z | |
dc.language.rfc3066 | en | |
dc.rights.holder | The author(s) | |
dspace.date.submission | 2025-09-01T07:55:09Z | |
mit.license | PUBLISHER_POLICY | |
mit.metadata.status | Authority Work and Publication Information Needed | en_US |