Unsupervised Conversion of 3D Models for Interactive Metaverses

Abstract

A virtual-world environment becomes a truly engaging platform when users have the ability to insert 3D content into the world. However, arbitrary 3D content is often not optimized for real-time rendering, limiting the ability of clients to display large scenes consisting of hundreds or thousands of objects. We present the design and implementation of an automatic, unsupervised conversion process that transforms 3D content into a format suitable for real-time rendering while minimizing loss of quality. The resulting progressive format includes a base mesh, allowing clients to quickly display the model, and a progressive portion for streaming additional detail as desired. Sirikata, an open virtual world platform, has processed over 700 models using this method.

Social Cognitive Theory to Assess the Intention to Participate in the Facebook Metaverse by Citizens in Peru during the COVID-19 Pandemic

“…There are reports describing system builds that help scalability into the metaverse, such as writing response times for massive activity such as the Massively Multiplayer Online Game (MMOG) [43,44], development of 3D models from the real world for integration into the metaverse [45,46], analysis programmed against cybercrime [47,48], multiplayers in the metaverse [20,49]. Moreover, it evaluated the interoperability of heterogeneous virtual environments in the metaverse [50,51].…”

Real-time visualization of building information models (BIM)

“…However, applying LOD per-object may not always lead to improved rendering performance. As object-based simplifications typically do not reduce the number of draw calls, this will only lead to increased rendering performance if the application is GPU-bound [34,35]. For CPU-bound scenarios it is therefore more suitable to consider hierarchical LOD (HLOD), where spatially coherent objects are simplified together instead of individually [36].…”

Identifying Key Factors to Distinguish Artificial and Human Avatars in the Metaverse: Insights from Software Practitioners

“…Imposing strict constraints on unoptimized data in the Metaverse could substantially reduce the availability of content and diminish the system's usability. Users should not be burdened with the complex, technical details of 3D content [3]. Mar Gonzales-Franco, a researcher at Microsoft, highlighted some challenges and deficiencies related to the Metaverse during her presentation at the ISMAR 2021 Symposium [4].…”