Our recent work MetaCube is accepted to be published in IEEE Communications Magazine. In this work, we propose 3D Crypto-dropout, which utilizes Web3 users’ information to generate unique fine-grained 3D models for metaverse.
Web3 (also known as Web 3.0) metaverse is a blockchain-driven networked, decentralized, and open virtual world. The key feature of the Web3 metaverse is that the ownership of digital assets is recorded by non-fungible token (NFT) protocol on the blockchain. Thus, users are better encouraged to construct Web3 metaverse due to the ownership of their user-generated content (UGC). However, the existing UGC editors mainly face two challenges: (1) they cannot guarantee the uniqueness of UGC; (2) they are hard to find a trade-off between model granularity and 3D modeling difficulty. In this paper, we design a novel UGC editor for the Web3 metaverse, named MetaCube, to address the aforementioned challenges. MetaCube applies an artificial intelligence (AI) method to assist the UGC creation for decreasing the 3D modeling difficulty while maintaining the model granularity.
To guarantee the uniqueness of UGC, this paper proposes 3D Crypto-dropout, a specially designed dropout that can utilize user information to control the UGC creation process and generate unique fine-grained 3D models. Our experimental results demonstrate that the proposed 3D Crypto-dropout can effectively guarantee the uniqueness of UGC from both numerical and human-centered evaluation. Moreover, the existing challenges and open research topics for the uniqueness of UGC are also profoundly discussed.
This is another collaborative work with White Matrix Inc.
Please cite this work with following information:
- Haihan Duan, Zhonghao Lin, Xiao Wu, and Wei Cai, “MetaCube: A Crypto-Based Unique User-Generated Content Editor for Web3 Metaverse“, IEEE Communications Magazine, 2023. [bib]