Publications

@inproceedings{behravan_transcending_2025,

title = {Transcending Dimensions Using Generative AI: Real-Time 3D Model Generation in Augmented Reality},

author = {M. Behravan and M. Haghani and D. Gračanin},

editor = {Chen J.Y.C. and Fragomeni G.},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105007690904&doi=10.1007%2f978-3-031-93700-2_2&partnerID=40&md5=1c4d643aad88d08cbbc9dd2c02413f10},

doi = {10.1007/978-3-031-93700-2_2},

isbn = {03029743 (ISSN); 978-303193699-9 (ISBN)},

year  = {2025},

date = {2025-01-01},

booktitle = {Lect. Notes Comput. Sci.},

volume = {15788 LNCS},

pages = {13–32},

publisher = {Springer Science and Business Media Deutschland GmbH},

abstract = {Traditional 3D modeling requires technical expertise, specialized software, and time-intensive processes, making it inaccessible for many users. Our research aims to lower these barriers by combining generative AI and augmented reality (AR) into a cohesive system that allows users to easily generate, manipulate, and interact with 3D models in real time, directly within AR environments. Utilizing cutting-edge AI models like Shap-E, we address the complex challenges of transforming 2D images into 3D representations in AR environments. Key challenges such as object isolation, handling intricate backgrounds, and achieving seamless user interaction are tackled through advanced object detection methods, such as Mask R-CNN. Evaluation results from 35 participants reveal an overall System Usability Scale (SUS) score of 69.64, with participants who engaged with AR/VR technologies more frequently rating the system significantly higher, at 80.71. This research is particularly relevant for applications in gaming, education, and AR-based e-commerce, offering intuitive, model creation for users without specialized skills. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.},

keywords = {3D Model Generation, 3D modeling, 3D models, 3d-modeling, Augmented Reality, Generative AI, Image-to-3D conversion, Model generation, Object Detection, Object recognition, Objects detection, Real- time, Specialized software, Technical expertise, Three dimensional computer graphics, Usability engineering},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{qin_utilizing_2024,

title = {Utilizing Generative AI for VR Exploration Testing: A Case Study},

author = {X. Qin and G. Weaver},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85213332710&doi=10.1145%2f3691621.3694955&partnerID=40&md5=8f3dc03520214cd2e270ed41a0fc0e19},

doi = {10.1145/3691621.3694955},

isbn = {979-840071249-4 (ISBN)},

year  = {2024},

date = {2024-01-01},

booktitle = {Proc. - ACM/IEEE Int. Conf. Autom. Softw. Eng. Workshops, ASEW},

pages = {228–232},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {As the virtual reality (VR) industry expands, the need for automated GUI testing for applications is growing rapidly. With its long-term memory and ability to process mixed data, including images and text, Generative AI (GenAI) shows the potential to understand complex user interfaces. In this paper, we conduct a case study to investigate the potential of using GenAI for field of view (FOV) analysis in VR exploration testing. Specifically, we examine how the model can assist in test entity selection and test action suggestions. Our experiments demonstrate that while GPT-4o achieves a 63% accuracy rate in object identification within an arbitrary FOV, it struggles with object organization and localization. We also identify critical contexts that can improve the accuracy of suggested actions across multiple FOVs. Finally, we discuss the limitations found during the experiment and offer insights into future research directions. © 2024 ACM.},

keywords = {Ability testing, Accuracy rate, Case Study, Case-studies, Entity selections, Field of views, Generative adversarial networks, GUI Exploration Testing, GUI testing, Localisation, Long term memory, Mixed data, Object identification, Object recognition, Virtual environments, Virtual Reality},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{joseph_iot_2023,

title = {IoT Empowered AI: Transforming Object Recognition and NLP Summarization with Generative AI},

author = {S. Joseph and B. S. Priya and R. Poorvaja and M. Santhosh Kumaran and S. Shivaraj and V. Jeyanth and R. P. Shivesh},

editor = {Arya K.V. and Wada T.},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189754688&doi=10.1109%2fCVMI59935.2023.10465077&partnerID=40&md5=9c1a9d7151c0b04bab83586f515d30aa},

doi = {10.1109/CVMI59935.2023.10465077},

isbn = {979-835030514-2 (ISBN)},

year  = {2023},

date = {2023-01-01},

booktitle = {Proc. IEEE Int. Conf. Comput. Vis. Mach. Intell., CVMI},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {In anticipation of the widespread adoption of augmented reality in the future, this paper introduces an advanced mobile application that seamlessly integrates AR and IoT technologies. The application aims to make these cutting-edge technologies more affordable and accessible to users while highlighting their immense benefits in assisting with household appliance control, as well as providing interactive and educational experiences. The app employs advanced algorithms such as object detection, Natural Language Processing (NLP), and Optical Character Recognition (OCR) to scan the smartphone's camera feed. Upon identification, AR controls for appliances, their power consumption, and electric bill tracking are displayed. Additionally, the application makes use of APIs to access the internet, retrieving relevant 3D generative models, 360-degree videos, 2D images, and textual information based on user interactions with detected objects. Users can effortlessly explore and interact with the 3D generative models using intuitive hand gestures, providing an immersive experience without the need for additional hardware or dedicated VR headsets. Beyond home automation, the app offers valuable educational benefits, serving as a unique learning tool for students to gain hands-on experience. Medical practitioners can quickly reference organ anatomy and utilize its feature-rich functionalities. Its cost-effectiveness, requiring only installation, ensures accessibility to a wide audience. The app's functionality is both intuitive and efficient, detecting objects in the camera feed and prompting user interactions. Users can select objects through simple hand gestures, choosing desired content like 3D generative models, 2D images, textual information, 360-degree videos, or shopping-related details. The app then retrieves and overlays the requested information onto the real-world view in AR. In conclusion, this groundbreaking AR and IoT -powered app revolutionizes home automation and learning experiences, leveraging only a smartphone's camera, without the need for additional hardware or expensive installations. Its potential applications extend to education, industries, and health care, making it a versatile and valuable tool for a broad range of users. © 2023 IEEE.},

keywords = {2D, 3D, Application program interface, Application Program Interface (API), Application program interfaces, Application programming interfaces (API), Application programs, Augmented Reality, Augmented Reality(AR), Automation, Cameras, Cost effectiveness, Domestic appliances, GenAl, Internet of Things, Internet of Things (IoT) technologies, Internet of things technologies, Language processing, Natural Language Processing, Natural language processing systems, Natural languages, Object Detection, Object recognition, Objects detection, Optical character recognition, Optical Character Recognition (OCR), Smartphones},

pubstate = {published},

tppubtype = {inproceedings}

}