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.
2025
Shao, Y.; You, W.; Zheng, Z.; Lu, Y.; Yang, C.; Zhou, Z.
CONDA: Introducing Context-Aware Decision Making Assistant in Virtual Reality for Interior Renovation Journal Article
In: International Journal of Human-Computer Interaction, vol. 41, no. 20, pp. 13239–13255, 2025, ISSN: 10447318 (ISSN); 15327590 (ISSN), (Publisher: Taylor and Francis Ltd.).
Abstract | Links | BibTeX | Tags: Computing formula, Context-aware decision makings, Contextual cue, Decision making, Decision-Making, Decisions makings, Design solutions, Driving demand, Interior Design, Interior designs, Interiors (building), Language Model, Large language model, large language models, Quality of life, Virtual environments, Virtual Reality
@article{shao_conda_2025,
title = {CONDA: Introducing Context-Aware Decision Making Assistant in Virtual Reality for Interior Renovation},
author = {Y. Shao and W. You and Z. Zheng and Y. Lu and C. Yang and Z. Zhou},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-86000228595&doi=10.1080%2F10447318.2025.2470285&partnerID=40&md5=0801b1854ec172c10a0cb374623cac77},
doi = {10.1080/10447318.2025.2470285},
issn = {10447318 (ISSN); 15327590 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {International Journal of Human-Computer Interaction},
volume = {41},
number = {20},
pages = {13239–13255},
abstract = {Customized interiors enhance quality of life and self-expression, driving demand for VR-based design solutions. However, scant research exists on exploiting contextual cues in VR to aid decision making. Consequently, we propose CONDA, a context-aware assistant which leveraging LLMs to support interior renovation decisions. Specifically, we reconstruct users’ homes in VR and provide CONDA with stylistic details and spatial layouts, allowing it to predict furniture labels based on the decision scenario. Besides, we devise various modes to comprehensively express users’ purchasing preferences. Finally, CONDA recommend compatible items based on the label matching algorithm, and generate multi-dimensional explanations. A 30-user study reveals contextual completeness and preference diversity critically influence recommendation quality and decision behaviors, with 90% praising CONDA’s performance and all expressing daily-use intent. Overall, we validated the efficacy and practicality of CONDA, deriving universal design insights for VR decision-support systems and establishing new research directions.CCS Concepts Human-centered computing (Formula presented.) Virtual reality Computing methodologies (Formula presented.) Natural language generation Applied computing (Formula presented.) Computer-aided design. © 2025 Elsevier B.V., All rights reserved.},
note = {Publisher: Taylor and Francis Ltd.},
keywords = {Computing formula, Context-aware decision makings, Contextual cue, Decision making, Decision-Making, Decisions makings, Design solutions, Driving demand, Interior Design, Interior designs, Interiors (building), Language Model, Large language model, large language models, Quality of life, Virtual environments, Virtual Reality},
pubstate = {published},
tppubtype = {article}
}
Customized interiors enhance quality of life and self-expression, driving demand for VR-based design solutions. However, scant research exists on exploiting contextual cues in VR to aid decision making. Consequently, we propose CONDA, a context-aware assistant which leveraging LLMs to support interior renovation decisions. Specifically, we reconstruct users’ homes in VR and provide CONDA with stylistic details and spatial layouts, allowing it to predict furniture labels based on the decision scenario. Besides, we devise various modes to comprehensively express users’ purchasing preferences. Finally, CONDA recommend compatible items based on the label matching algorithm, and generate multi-dimensional explanations. A 30-user study reveals contextual completeness and preference diversity critically influence recommendation quality and decision behaviors, with 90% praising CONDA’s performance and all expressing daily-use intent. Overall, we validated the efficacy and practicality of CONDA, deriving universal design insights for VR decision-support systems and establishing new research directions.CCS Concepts Human-centered computing (Formula presented.) Virtual reality Computing methodologies (Formula presented.) Natural language generation Applied computing (Formula presented.) Computer-aided design. © 2025 Elsevier B.V., All rights reserved.
2023
Le, M. -H.; Chu, C. -B.; Le, K. -D.; Nguyen, T. V.; Tran, M. -T.; Le, T. -N.
VIDES: Virtual Interior Design via Natural Language and Visual Guidance Proceedings Article
In: Bruder, G.; Olivier, A. H.; Cunningham, A.; Peng, E. Y.; Grubert, J.; Williams, I. (Ed.): Proc. - IEEE Int. Symp. Mixed Augment. Real. Adjunct, ISMAR-Adjunct, pp. 689–694, Institute of Electrical and Electronics Engineers Inc., 2023, ISBN: 9798350328912 (ISBN).
Abstract | Links | BibTeX | Tags: Architectural design, Customisation, Cutting edge technology, Design concept, Design systems, Image editing, Image generation, Image generations, Indoor space, Interior Design, Interior designs, Interiors (building), Natural languages, Virtual Reality, Visual guidance, Visual languages
@inproceedings{le_vides_2023,
title = {VIDES: Virtual Interior Design via Natural Language and Visual Guidance},
author = {M. -H. Le and C. -B. Chu and K. -D. Le and T. V. Nguyen and M. -T. Tran and T. -N. Le},
editor = {G. Bruder and A. H. Olivier and A. Cunningham and E. Y. Peng and J. Grubert and I. Williams},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85180376943&doi=10.1109%2FISMAR-Adjunct60411.2023.00148&partnerID=40&md5=3bf65eb54aa7649ca195dc2481d47d22},
doi = {10.1109/ISMAR-Adjunct60411.2023.00148},
isbn = {9798350328912 (ISBN)},
year = {2023},
date = {2023-01-01},
booktitle = {Proc. - IEEE Int. Symp. Mixed Augment. Real. Adjunct, ISMAR-Adjunct},
pages = {689–694},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Interior design is crucial in creating aesthetically pleasing and functional indoor spaces. However, developing and editing interior design concepts requires significant time and expertise. We propose Virtual Interior DESign (VIDES) system in response to this challenge. Leveraging cutting-edge technology in generative AI, our system can assist users in generating and editing indoor scene concepts quickly, given user text description and visual guidance. Using both visual guidance and language as the conditional inputs significantly enhances the accuracy and coherence of the generated scenes, resulting in visually appealing designs. Through extensive experimentation, we demonstrate the effectiveness of VIDES in developing new indoor concepts, changing indoor styles, and replacing and removing interior objects. The system successfully captures the essence of users' descriptions while providing flexibility for customization. Consequently, this system can potentially reduce the entry barrier for indoor design, making it more accessible to users with limited technical skills and reducing the time required to create high-quality images. Individuals who have a background in design can now easily communicate their ideas visually and effectively present their design concepts. © 2023 Elsevier B.V., All rights reserved.},
keywords = {Architectural design, Customisation, Cutting edge technology, Design concept, Design systems, Image editing, Image generation, Image generations, Indoor space, Interior Design, Interior designs, Interiors (building), Natural languages, Virtual Reality, Visual guidance, Visual languages},
pubstate = {published},
tppubtype = {inproceedings}
}
Interior design is crucial in creating aesthetically pleasing and functional indoor spaces. However, developing and editing interior design concepts requires significant time and expertise. We propose Virtual Interior DESign (VIDES) system in response to this challenge. Leveraging cutting-edge technology in generative AI, our system can assist users in generating and editing indoor scene concepts quickly, given user text description and visual guidance. Using both visual guidance and language as the conditional inputs significantly enhances the accuracy and coherence of the generated scenes, resulting in visually appealing designs. Through extensive experimentation, we demonstrate the effectiveness of VIDES in developing new indoor concepts, changing indoor styles, and replacing and removing interior objects. The system successfully captures the essence of users' descriptions while providing flexibility for customization. Consequently, this system can potentially reduce the entry barrier for indoor design, making it more accessible to users with limited technical skills and reducing the time required to create high-quality images. Individuals who have a background in design can now easily communicate their ideas visually and effectively present their design concepts. © 2023 Elsevier B.V., All rights reserved.
Yeo, J. Q.; Wang, Y.; Tanary, S.; Cheng, J.; Lau, M.; Ng, A. B.; Guan, F.
AICRID: AI-Empowered CR For Interior Design Proceedings Article
In: Bruder, G.; Olivier, A. H.; Cunningham, A.; Peng, E. Y.; Grubert, J.; Williams, I. (Ed.): Proc. - IEEE Int. Symp. Mixed Augment. Real. Adjunct, ISMAR-Adjunct, pp. 837–841, Institute of Electrical and Electronics Engineers Inc., 2023, ISBN: 9798350328912 (ISBN).
Abstract | Links | BibTeX | Tags: 3D modeling, 3D models, 3d-modeling, Architectural design, Artificial intelligence, Artificial intelligence technologies, Augmented Reality, Augmented reality technology, Interior Design, Interior designs, machine learning, Machine-learning, Model generation, Novel design, Text images, User need, Visualization
@inproceedings{yeo_aicrid_2023,
title = {AICRID: AI-Empowered CR For Interior Design},
author = {J. Q. Yeo and Y. Wang and S. Tanary and J. Cheng and M. Lau and A. B. Ng and F. Guan},
editor = {G. Bruder and A. H. Olivier and A. Cunningham and E. Y. Peng and J. Grubert and I. Williams},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85180375829&doi=10.1109%2FISMAR-Adjunct60411.2023.00184&partnerID=40&md5=b059c45229401ab10f5a0f0bea711232},
doi = {10.1109/ISMAR-Adjunct60411.2023.00184},
isbn = {9798350328912 (ISBN)},
year = {2023},
date = {2023-01-01},
booktitle = {Proc. - IEEE Int. Symp. Mixed Augment. Real. Adjunct, ISMAR-Adjunct},
pages = {837–841},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Augmented Reality (AR) technologies have been utilized for interior design for years. Normally 3D furniture models need to be created manually or by scanning with specialized devices and this is usually a costly process. Additionally, users need controllers or hands for manipulating the virtual furniture which may lead to fatigue for long-time usage. Artificial Intelligence (AI) technologies have made it possible to generate 3D models from texts, images or both and show potential to automate interactions through the user's voice. We propose a novel design, AICRID in short, which aims to automate the 3D model generation and to facilitate the interactions for interior design AR by leveraging on AI technologies. Specifically, our design will allow the users to directly generate 3D furniture models with generative AI, enabling them to directly interact with the virtual objects through their voices. © 2023 Elsevier B.V., All rights reserved.},
keywords = {3D modeling, 3D models, 3d-modeling, Architectural design, Artificial intelligence, Artificial intelligence technologies, Augmented Reality, Augmented reality technology, Interior Design, Interior designs, machine learning, Machine-learning, Model generation, Novel design, Text images, User need, Visualization},
pubstate = {published},
tppubtype = {inproceedings}
}
Augmented Reality (AR) technologies have been utilized for interior design for years. Normally 3D furniture models need to be created manually or by scanning with specialized devices and this is usually a costly process. Additionally, users need controllers or hands for manipulating the virtual furniture which may lead to fatigue for long-time usage. Artificial Intelligence (AI) technologies have made it possible to generate 3D models from texts, images or both and show potential to automate interactions through the user's voice. We propose a novel design, AICRID in short, which aims to automate the 3D model generation and to facilitate the interactions for interior design AR by leveraging on AI technologies. Specifically, our design will allow the users to directly generate 3D furniture models with generative AI, enabling them to directly interact with the virtual objects through their voices. © 2023 Elsevier B.V., All rights reserved.