26/04/2025
📣 Great Team and Great Paper! 👏
👾 We’re really excited at to see , , and teaming up! 🤩
💡 Paper: "MineVRA: Exploring the Role of Generative AI-Driven Content Development in XR Environments through a Context-Aware Approach" - IEEE Transactions on Visualization and Computer Graphics.
🧠 Authors:
Emiliano Santarnecchi - Harvard Medical School, Precision Neuroscience & Neuromodulation Program, Network Control Laboratory at the Gordon Center for Medical Imaging at Massachusetts General Hospital, Horizon Neuroscience, Boston, MA, hashtag
Emanuele Balloni - DII, Università Politecnica delle Marche, hashtag
Marina Paolanti - SPOCRI, Università degli Studi di Macerata, hashtag
Emanuele Frontoni - SPOCRI, Università degli Studi di Macerata, hashtag
Lorenzo Stacchio - SPOCRI, Università degli Studi di Macerata, hashtag
Primo Zingaretti - DII, Università Politecnica delle Marche, hashtag
Roberto Pierdicca - DICEA, Università Politecnica delle Marche, hashtag
🤖 The convergence of Artificial Intelligence (AI), Computer Vision (CV), Computer Graphics (CG), and Extended Reality (XR) is currently driving innovation within immersive environments. One of the main challenges in these settings is the creation of personalized 3D assets, which has traditionally relied on manual modeling — a time-consuming process that often falls short of meeting individual user needs.
Recently, Generative AI (GenAI) has emerged as a promising solution for automated, context-aware content generation.
In this paper, we introduce MineVRA (MultImodal generative artificial iNtelligence for contExt-aware Virtual Reality Assets), a novel Human-In-The-Loop (HITL) XR framework that integrates GenAI to enable coherent and adaptive 3D content creation in immersive scenarios.
To assess the effectiveness of this approach, we conducted a comparative user study evaluating the performance and user satisfaction of GenAI-generated 3D objects versus those produced by Sketchfab across various immersive contexts.
The findings suggest that GenAI can significantly complement traditional 3D asset libraries, offering valuable design implications for the development of human-centered XR environments.
✅ More info: https://lnkd.in/dmjaRmmb
IEEE Computer Society Harvard University Harvard Medical School Univpm Università Politecnica delle Marche Unimc / Università degli Studi di Macerata IEEE
