AHCI RESEARCH GROUP
Publications
Papers published in international journals,
proceedings of conferences, workshops and books.
OUR RESEARCH
Scientific Publications
How to
Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
2024
Chen, X.; Gao, W.; Chu, Y.; Song, Y.
Enhancing interaction in virtual-real architectural environments: A comparative analysis of generative AI-driven reality approaches Journal Article
In: Building and Environment, vol. 266, 2024, ISSN: 03601323 (ISSN).
Abstract | Links | BibTeX | Tags: Architectural design, Architectural environment, Architectural environments, Artificial intelligence, cluster analysis, Comparative analyzes, comparative study, Computational design, Generative adversarial networks, Generative AI, generative artificial intelligence, Mixed reality, Real time interactions, Real-space, Unity3d, Virtual addresses, Virtual environments, Virtual Reality, Virtual spaces, Work-flows
@article{chen_enhancing_2024,
title = {Enhancing interaction in virtual-real architectural environments: A comparative analysis of generative AI-driven reality approaches},
author = {X. Chen and W. Gao and Y. Chu and Y. Song},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85205298350&doi=10.1016%2fj.buildenv.2024.112113&partnerID=40&md5=8c7d4f5477e25b021dfc5e013a851620},
doi = {10.1016/j.buildenv.2024.112113},
issn = {03601323 (ISSN)},
year = {2024},
date = {2024-01-01},
journal = {Building and Environment},
volume = {266},
abstract = {The architectural environment is expanding into digital, virtual, and informational dimensions, introducing challenges in virtual-real space interaction. Traditional design methods struggle with real-time interaction, integration with existing workflows, and rapid space modification. To address these issues, we present a generative design method that enables symbiotic interaction between virtual and real spaces using Mixed Reality (MR) and Generative Artificial Intelligence (AI) technologies. We developed two approaches: one using the Rhino modeling platform and the other based on the Unity3D game engine, tailored to different application needs. User experience testing in exhibition, leisure, and residential spaces evaluated our method's effectiveness. Results showed significant improvements in design flexibility, interactive efficiency, and user satisfaction. In the exhibition scenario, the Unity3D-based method excelled in rapid design modifications and immersive experiences. Questionnaire data indicated that MR offers good visual comfort and higher immersion than VR, effectively supporting architects in interface and scale design. Clustering analysis of participants' position and gaze data revealed diverse behavioral patterns in the virtual-physical exhibition space, providing insights for optimizing spatial layouts and interaction methods. Our findings suggest that the generative AI-driven MR method simplifies traditional design processes by enabling real-time modification and interaction with spatial interfaces through simple verbal and motion interactions. This approach streamlines workflows by reducing steps like measuring, modeling, and rendering, while enhancing user engagement and creativity. Overall, this method offers new possibilities for experiential exhibition and architectural design, contributing to future environments where virtual and real spaces coexist seamlessly. © 2024},
keywords = {Architectural design, Architectural environment, Architectural environments, Artificial intelligence, cluster analysis, Comparative analyzes, comparative study, Computational design, Generative adversarial networks, Generative AI, generative artificial intelligence, Mixed reality, Real time interactions, Real-space, Unity3d, Virtual addresses, Virtual environments, Virtual Reality, Virtual spaces, Work-flows},
pubstate = {published},
tppubtype = {article}
}
The architectural environment is expanding into digital, virtual, and informational dimensions, introducing challenges in virtual-real space interaction. Traditional design methods struggle with real-time interaction, integration with existing workflows, and rapid space modification. To address these issues, we present a generative design method that enables symbiotic interaction between virtual and real spaces using Mixed Reality (MR) and Generative Artificial Intelligence (AI) technologies. We developed two approaches: one using the Rhino modeling platform and the other based on the Unity3D game engine, tailored to different application needs. User experience testing in exhibition, leisure, and residential spaces evaluated our method's effectiveness. Results showed significant improvements in design flexibility, interactive efficiency, and user satisfaction. In the exhibition scenario, the Unity3D-based method excelled in rapid design modifications and immersive experiences. Questionnaire data indicated that MR offers good visual comfort and higher immersion than VR, effectively supporting architects in interface and scale design. Clustering analysis of participants' position and gaze data revealed diverse behavioral patterns in the virtual-physical exhibition space, providing insights for optimizing spatial layouts and interaction methods. Our findings suggest that the generative AI-driven MR method simplifies traditional design processes by enabling real-time modification and interaction with spatial interfaces through simple verbal and motion interactions. This approach streamlines workflows by reducing steps like measuring, modeling, and rendering, while enhancing user engagement and creativity. Overall, this method offers new possibilities for experiential exhibition and architectural design, contributing to future environments where virtual and real spaces coexist seamlessly. © 2024
2023
Kouzelis, L. R.; Spantidi, O.
Synthesizing Play-Ready VR Scenes with Natural Language Prompts Through GPT API Proceedings Article
In: G., Bebis; G., Ghiasi; Y., Fang; A., Sharf; Y., Dong; C., Weaver; Z., Leo; J.J., LaViola Jr.; L., Kohli (Ed.): Lect. Notes Comput. Sci., pp. 15–26, Springer Science and Business Media Deutschland GmbH, 2023, ISBN: 03029743 (ISSN); 978-303147965-6 (ISBN).
Abstract | Links | BibTeX | Tags: 3-d designs, 3D object, 3D scenes, AI-driven 3D Design, Language Model, Natural languages, Novel methodology, Scene Generation, Three dimensional computer graphics, Unity3d, Virtual Reality, Visual computing
@inproceedings{kouzelis_synthesizing_2023,
title = {Synthesizing Play-Ready VR Scenes with Natural Language Prompts Through GPT API},
author = {L. R. Kouzelis and O. Spantidi},
editor = {Bebis G. and Ghiasi G. and Fang Y. and Sharf A. and Dong Y. and Weaver C. and Leo Z. and LaViola Jr. J.J. and Kohli L.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85180626887&doi=10.1007%2f978-3-031-47966-3_2&partnerID=40&md5=d15c3e2f3260e2a68bdca91c29df7bbb},
doi = {10.1007/978-3-031-47966-3_2},
isbn = {03029743 (ISSN); 978-303147965-6 (ISBN)},
year = {2023},
date = {2023-01-01},
booktitle = {Lect. Notes Comput. Sci.},
volume = {14362},
pages = {15–26},
publisher = {Springer Science and Business Media Deutschland GmbH},
abstract = {In visual computing, 3D scene generation stands as a crucial component, offering applications in various fields such as gaming, virtual reality (VR), and architectural visualization. Creating realistic and versatile virtual environments, however, poses significant challenges. This work presents a novel methodology that leverages the capabilities of a widely adopted large language model (LLM) to address these challenges. Our approach utilizes the GPT API to interpret natural language prompts and generate detailed, VR-ready scenes within Unity3D. Our work is also inherently scalable, since the model accepts any database of 3D objects with minimal prior configuration. The effectiveness of the proposed system is demonstrated through a series of case studies, revealing its potential to generate diverse and functional virtual spaces. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.},
keywords = {3-d designs, 3D object, 3D scenes, AI-driven 3D Design, Language Model, Natural languages, Novel methodology, Scene Generation, Three dimensional computer graphics, Unity3d, Virtual Reality, Visual computing},
pubstate = {published},
tppubtype = {inproceedings}
}
In visual computing, 3D scene generation stands as a crucial component, offering applications in various fields such as gaming, virtual reality (VR), and architectural visualization. Creating realistic and versatile virtual environments, however, poses significant challenges. This work presents a novel methodology that leverages the capabilities of a widely adopted large language model (LLM) to address these challenges. Our approach utilizes the GPT API to interpret natural language prompts and generate detailed, VR-ready scenes within Unity3D. Our work is also inherently scalable, since the model accepts any database of 3D objects with minimal prior configuration. The effectiveness of the proposed system is demonstrated through a series of case studies, revealing its potential to generate diverse and functional virtual spaces. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.