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
Kurai, R.; Hiraki, T.; Hiroi, Y.; Hirao, Y.; Perusquía-Hernández, M.; Uchiyama, H.; Kiyokawa, K.
An implementation of MagicCraft: Generating Interactive 3D Objects and Their Behaviors from Text for Commercial Metaverse Platforms Proceedings Article
In: Proc. - IEEE Conf. Virtual Real. 3D User Interfaces Abstr. Workshops, VRW, pp. 1284–1285, Institute of Electrical and Electronics Engineers Inc., 2025, ISBN: 9798331514846 (ISBN).
Abstract | Links | BibTeX | Tags: 3D modeling, 3D models, 3D object, 3D Object Generation, 3d-modeling, AI-Assisted Design, Generative AI, Immersive, Metaverse, Metaverses, Model skill, Object oriented programming, Programming skills
@inproceedings{kurai_implementation_2025,
title = {An implementation of MagicCraft: Generating Interactive 3D Objects and Their Behaviors from Text for Commercial Metaverse Platforms},
author = {R. Kurai and T. Hiraki and Y. Hiroi and Y. Hirao and M. Perusquía-Hernández and H. Uchiyama and K. Kiyokawa},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105005153642&doi=10.1109%2FVRW66409.2025.00288&partnerID=40&md5=fd6d3b8d0dcbc5b9ccd4c31069bb4f4a},
doi = {10.1109/VRW66409.2025.00288},
isbn = {9798331514846 (ISBN)},
year = {2025},
date = {2025-01-01},
booktitle = {Proc. - IEEE Conf. Virtual Real. 3D User Interfaces Abstr. Workshops, VRW},
pages = {1284–1285},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Metaverse platforms are rapidly evolving to provide immersive spaces. However, the generation of dynamic and interactive 3D objects remains a challenge due to the need for advanced 3D modeling and programming skills. We present MagicCraft, a system that generates functional 3D objects from natural language prompts. MagicCraft uses generative AI models to manage the entire content creation pipeline: converting user text descriptions into images, transforming images into 3D models, predicting object behavior, and assigning necessary attributes and scripts. It also provides an interactive interface for users to refine generated objects by adjusting features like orientation, scale, seating positions, and grip points. © 2025 Elsevier B.V., All rights reserved.},
keywords = {3D modeling, 3D models, 3D object, 3D Object Generation, 3d-modeling, AI-Assisted Design, Generative AI, Immersive, Metaverse, Metaverses, Model skill, Object oriented programming, Programming skills},
pubstate = {published},
tppubtype = {inproceedings}
}
Metaverse platforms are rapidly evolving to provide immersive spaces. However, the generation of dynamic and interactive 3D objects remains a challenge due to the need for advanced 3D modeling and programming skills. We present MagicCraft, a system that generates functional 3D objects from natural language prompts. MagicCraft uses generative AI models to manage the entire content creation pipeline: converting user text descriptions into images, transforming images into 3D models, predicting object behavior, and assigning necessary attributes and scripts. It also provides an interactive interface for users to refine generated objects by adjusting features like orientation, scale, seating positions, and grip points. © 2025 Elsevier B.V., All rights reserved.
Kurai, R.; Hiraki, T.; Hiroi, Y.; Hirao, Y.; Perusquía-Hernández, M.; Uchiyama, H.; Kiyokawa, K.
MagicCraft: Natural Language-Driven Generation of Dynamic and Interactive 3D Objects for Commercial Metaverse Platforms Journal Article
In: IEEE Access, vol. 13, pp. 132459–132474, 2025, ISSN: 21693536 (ISSN), (Publisher: Institute of Electrical and Electronics Engineers Inc.).
Abstract | Links | BibTeX | Tags: 3D models, 3D object, 3D Object Generation, 3d-modeling, AI-Assisted Design, Artificial intelligence, Behavioral Research, Content creation, Generative AI, Immersive, Metaverse, Metaverses, Natural language processing systems, Natural languages, Object oriented programming, Three dimensional computer graphics, user experience, User interfaces
@article{kurai_magiccraft_2025,
title = {MagicCraft: Natural Language-Driven Generation of Dynamic and Interactive 3D Objects for Commercial Metaverse Platforms},
author = {R. Kurai and T. Hiraki and Y. Hiroi and Y. Hirao and M. Perusquía-Hernández and H. Uchiyama and K. Kiyokawa},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105010187256&doi=10.1109%2FACCESS.2025.3587232&partnerID=40&md5=9b7a8115c62a8f9da4956dbbbb53dc4e},
doi = {10.1109/ACCESS.2025.3587232},
issn = {21693536 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {IEEE Access},
volume = {13},
pages = {132459–132474},
abstract = {Metaverse platforms are rapidly evolving to provide immersive spaces for user interaction and content creation. However, the generation of dynamic and interactive 3D objects remains challenging due to the need for advanced 3D modeling and programming skills. To address this challenge, we present MagicCraft, a system that generates functional 3D objects from natural language prompts for metaverse platforms. MagicCraft uses generative AI models to manage the entire content creation pipeline: converting user text descriptions into images, transforming images into 3D models, predicting object behavior, and assigning necessary attributes and scripts. It also provides an interactive interface for users to refine generated objects by adjusting features such as orientation, scale, seating positions, and grip points. Implemented on Cluster, a commercial metaverse platform, MagicCraft was evaluated by 7 expert CG designers and 51 general users. Results show that MagicCraft significantly reduces the time and skill required to create 3D objects. Users with no prior experience in 3D modeling or programming successfully created complex, interactive objects and deployed them in the metaverse. Expert feedback highlighted the system's potential to improve content creation workflows and support rapid prototyping. By integrating AI-generated content into metaverse platforms, MagicCraft makes 3D content creation more accessible. © 2025 Elsevier B.V., All rights reserved.},
note = {Publisher: Institute of Electrical and Electronics Engineers Inc.},
keywords = {3D models, 3D object, 3D Object Generation, 3d-modeling, AI-Assisted Design, Artificial intelligence, Behavioral Research, Content creation, Generative AI, Immersive, Metaverse, Metaverses, Natural language processing systems, Natural languages, Object oriented programming, Three dimensional computer graphics, user experience, User interfaces},
pubstate = {published},
tppubtype = {article}
}
Metaverse platforms are rapidly evolving to provide immersive spaces for user interaction and content creation. However, the generation of dynamic and interactive 3D objects remains challenging due to the need for advanced 3D modeling and programming skills. To address this challenge, we present MagicCraft, a system that generates functional 3D objects from natural language prompts for metaverse platforms. MagicCraft uses generative AI models to manage the entire content creation pipeline: converting user text descriptions into images, transforming images into 3D models, predicting object behavior, and assigning necessary attributes and scripts. It also provides an interactive interface for users to refine generated objects by adjusting features such as orientation, scale, seating positions, and grip points. Implemented on Cluster, a commercial metaverse platform, MagicCraft was evaluated by 7 expert CG designers and 51 general users. Results show that MagicCraft significantly reduces the time and skill required to create 3D objects. Users with no prior experience in 3D modeling or programming successfully created complex, interactive objects and deployed them in the metaverse. Expert feedback highlighted the system's potential to improve content creation workflows and support rapid prototyping. By integrating AI-generated content into metaverse platforms, MagicCraft makes 3D content creation more accessible. © 2025 Elsevier B.V., All rights reserved.
Kai, W. -H.; Xing, K. -X.
Video-driven musical composition using large language model with memory-augmented state space Journal Article
In: Visual Computer, vol. 41, no. 5, pp. 3345–3357, 2025, ISSN: 01782789 (ISSN); 14322315 (ISSN), (Publisher: Springer Science and Business Media Deutschland GmbH).
Abstract | Links | BibTeX | Tags: 'current, Associative storage, Augmented Reality, Augmented state space, Computer simulation languages, Computer system recovery, Distributed computer systems, HTTP, Language Model, Large language model, Long-term video-to-music generation, Mamba, Memory architecture, Memory-augmented, Modeling languages, Music, Musical composition, Natural language processing systems, Object oriented programming, Performance, Problem oriented languages, State space, State-space
@article{kai_video-driven_2025,
title = {Video-driven musical composition using large language model with memory-augmented state space},
author = {W. -H. Kai and K. -X. Xing},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105001073242&doi=10.1007%2Fs00371-024-03606-w&partnerID=40&md5=71a40ea7584c5a5f210afc1c30aac468},
doi = {10.1007/s00371-024-03606-w},
issn = {01782789 (ISSN); 14322315 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {Visual Computer},
volume = {41},
number = {5},
pages = {3345–3357},
abstract = {The current landscape of research leveraging large language models (LLMs) is experiencing a surge. Many works harness the powerful reasoning capabilities of these models to comprehend various modalities, such as text, speech, images, videos, etc. However, the research work on LLms for music inspiration is still in its infancy. To fill the gap in this field and break through the dilemma that LLMs can only understand short videos with limited frames, we propose a large language model with state space for long-term video-to-music generation. To capture long-range dependency and maintaining high performance, while further decrease the computing cost, our overall network includes the Enhanced Video Mamba, which incorporates continuous moving window partitioning and local feature augmentation, and a long-term memory bank that captures and aggregates historical video information to mitigate information loss in long sequences. This framework achieves both subquadratic-time computation and near-linear memory complexity, enabling effective long-term video-to-music generation. We conduct a thorough evaluation of our proposed framework. The experimental results demonstrate that our model achieves or surpasses the performance of the current state-of-the-art models. Our code released on https://github.com/kai211233/S2L2-V2M. © 2025 Elsevier B.V., All rights reserved.},
note = {Publisher: Springer Science and Business Media Deutschland GmbH},
keywords = {'current, Associative storage, Augmented Reality, Augmented state space, Computer simulation languages, Computer system recovery, Distributed computer systems, HTTP, Language Model, Large language model, Long-term video-to-music generation, Mamba, Memory architecture, Memory-augmented, Modeling languages, Music, Musical composition, Natural language processing systems, Object oriented programming, Performance, Problem oriented languages, State space, State-space},
pubstate = {published},
tppubtype = {article}
}
The current landscape of research leveraging large language models (LLMs) is experiencing a surge. Many works harness the powerful reasoning capabilities of these models to comprehend various modalities, such as text, speech, images, videos, etc. However, the research work on LLms for music inspiration is still in its infancy. To fill the gap in this field and break through the dilemma that LLMs can only understand short videos with limited frames, we propose a large language model with state space for long-term video-to-music generation. To capture long-range dependency and maintaining high performance, while further decrease the computing cost, our overall network includes the Enhanced Video Mamba, which incorporates continuous moving window partitioning and local feature augmentation, and a long-term memory bank that captures and aggregates historical video information to mitigate information loss in long sequences. This framework achieves both subquadratic-time computation and near-linear memory complexity, enabling effective long-term video-to-music generation. We conduct a thorough evaluation of our proposed framework. The experimental results demonstrate that our model achieves or surpasses the performance of the current state-of-the-art models. Our code released on https://github.com/kai211233/S2L2-V2M. © 2025 Elsevier B.V., All rights reserved.