Home / Current Issue / Paper 1712135
AI Based 2d to 3d Image Conversion with Web-AR Visualization
Subject area: Science,Engineering and Technology · Area of research: Machine Learning
DOI: https://doi.org/10.64388/IREV9I5-1712135
Abstract
Artificial Intelligence (AI) and Augmented Reality (AR) have transformed how we approach visual computing in education. This research presents a system that turns two-dimensional (2D) educational images into interactive three-dimensional (3D) AR experiences, which can be accessed through web browsers using WebAR technologies like AR.js and Three.js. The method utilizes deep learning models? specifically convolutional neural networks (CNNs) and transformer based depth prediction networks?to extract depth information and create realistic 3D structures. The result is an engaging platform where learners can interact with 3D models displayed in augmented reality, enhancing their educational experience. Experimental results show notable improvements in student engagement, understanding, and information retention. This approach holds great potential for applications in STEM education, digital museums, and architectural visualization, highlighting its scalability and accessibility across various devices.
Keywords
2D to 3D; Artificial intelligence; Augmented Reality
References
[1] D. Eigen, C. Puhrsch, and R. Fergus, "Depth Map Prediction from a Single Image using a Multi-Scale Deep Network," in Advances in Neural Information Processing Systems, 2014.
[2] I. Laina, C. Rupprecht, V. Belagiannis, F. Tombari, and N. Navab, "Deeper Depth Prediction with Fully Convolutional Residual
[3] Networks," in Proceedings of the International Conference on 3D Vision (3DV), 2016.
[4] C. Godard, O. Mac Aodha, and G. J. Brostow, "Unsupervised Monocular Depth Estimation with Left-Right Consistency," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[5] R. Ranftl, A. Bochkovskiy, and V. Koltun, "Vision Transformers for Dense Prediction," in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021.
[6] M. Billinghurst, A. Clark, and G. Lee, "A Survey of Augmented Reality," Foundations and Trends in Human–Computer Interaction, vol. 8, no. 2–3, pp. 73–272, 2014.
[7] T. Weng, X. Chen, and Y. Zhao, "The Application of WebAR in STEM Education," Journal of Interactive Learning Research, vol. 33, no. 4, pp. 575–592, 2022.
[8] Y. Zhao et al., "Augmented Reality Learning Tools: Enhancing Student Engagement," Computers & Education, vol. 198, 2023.
[9] R. Winkler and M. Söllner, "Unleashing the Potential of Chatbots in Education: A Stateofthe-Art Analysis," ACM Transactions on Computer-Human Interaction, 2022.
How to cite this paper
@article{1712135,
author = {Anushree S D, Charvi M, Deepika T V, Kusuma M, Satish .T},
title = {AI Based 2d to 3d Image Conversion with Web-AR Visualization},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {5},
pages = {1123-1127},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1712135.pdf},
abstract = {Artificial Intelligence (AI) and Augmented Reality (AR) have transformed how we approach visual computing in education. This research presents a system that turns two-dimensional (2D) educational images into interactive three-dimensional (3D) AR experiences, which can be accessed through web browsers using WebAR technologies like AR.js and Three.js. The method utilizes deep learning models? specifically convolutional neural networks (CNNs) and transformer based depth prediction networks?to extract depth information and create realistic 3D structures. The result is an engaging platform where learners can interact with 3D models displayed in augmented reality, enhancing their educational experience. Experimental results show notable improvements in student engagement, understanding, and information retention. This approach holds great potential for applications in STEM education, digital museums, and architectural visualization, highlighting its scalability and accessibility across various devices.},
keywords = {2D to 3D; Artificial intelligence; Augmented Reality},
month = {November},
doi = {https://doi.org/10.64388/IREV9I5-1712135}
}