Author : Nidhi Singh 1
Date of Publication :12th August 2021
Abstract: Augmented Reality allows integration of 3D virtual objects into the real environment in real time thus allowing users to relate with their physical environment and making the experience more interesting. The manual conversion of the 2D images to 3D models is a tedious and time-consuming process. Hence, in this project, we automate the process of reconstruction of 3D models from 2D images using Convolutional Neural Networks (CNN). We develop a Depth-based image in the initial stage combined with CNN followed by the structural recovery and creating prediction to achieve the desired model using another CNN model. The reconstruction starts with less resolution which grows iteratively. Lastly, they are optimized using Stochastic Gradient Descent which makes them fit for use in Augmented Reality. This process of automated 2D-3D conversion is integrated with marker-less implementation of Augmented Reality through an Android Application to ultimately visualize furniture in the real world.
- J. He et al., "The research and application of the augmented reality technology," 2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), Chengdu, 2017, pp. 496-501, doi: 10.1109/ITNEC.2017.8284781.
- Cao, Sheng & Wang, Qian. (2017) “Application and Prospect of AR Technology in E-commerce” 10.2991/emcs-17.2017.262.
- Viyanon, Waraporn, Thanadon Songsuittipong, Phattarika Piyapaisarn and Suwanun Sudchid. “AR Furniture: Integrating Augmented Reality Technology to Enhance Interior Design using Marker and Markerless tracking.” IIP'17 (2017).
- Ms. Kirti Motwani, Shweta Sharma, Dhanashree Pawar, “Furniture Arrangement Using Augmented Reality” in International Research Journal of Engineering and Technology (IRJET), Volume: 04 Issue: 04, Apr -2017.
- M. Khedwala, F. Momin, U. Pachhapure and S. Shaikh, "Analysis of Auto Generation of 3D Model Using Multiple 2D Graphics to Manifest Through Augmented Reality," 2018 International Conference on Smart City and Emerging Technology (ICSCET), Mumbai, 2018, pp. 1-5, doi: 10.1109/ICSCET.2018.8537310.
- K. Sakai and Y. Yasumura, "Three-dimensional shape reconstruction from a single image based on feature learning," 2018 International Workshop on Advanced Image Technology (IWAIT), Chiang Mai, 2018, pp. 1-4, doi: 10.1109/IWAIT.2018.8369636.
- L. Li, X. Qiao, Q. Lu, P. Ren and R. Lin, "Rendering Optimization for Mobile Web 3D Based on Animation Data Separation and On-Demand Loading," in IEEE Access, vol. 8, pp. 88474-88486, 2020, doi: 10.1109/ACCESS.2020.2993613.
- Boonbrahm, Salin & Boonbrahm, Poonpong & Kaewrat, Charlee. (2020) “The Use of Marker-Based Augmented Reality in Space Measurement” Procedia Manufacturing. 42. 337-343. 10.1016/j.promfg.2020.02.081.
- Amin, Dhiraj & Govilkar, Sharvari. (2015) “Comparative Study of Augmented Reality Sdk's” International Journal on Computational Science & Applications. 5. 11-26. 10.5121/ijcsa.2015.5102.
- Kasetty sudarshan, Sneha. (2017). AUGMENTED REALITY IN MOBILE DEVICES.
- Galabov, Miroslav. (2015), “A Real Time 2D to 3D Image Conversion Techniques” International Journal of Engineering Science and Innovative Technology. 4. 297-304.
- Stigeborn, P. (2018). Generating 3D-objects using neural networks [Published bachelor‟s thesis]. KTH Royal Institute Of Technology.