Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{190054,
        author = {Dhirajkumar Pachling and Sarth Gaikwad and Pratik Vidhate and Diksha Kapse and Mrs. Nita Mahale},
        title = {Skematix: Automated AI-Based Conversion of 2D Floor Plans into 3D and AR Visualizations},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {3486-3488},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190054},
        abstract = {Architectural designs are predominantly communicated using two-dimensional (2D) floor plans, which often fail to provide an intuitive understanding of spatial relationships for non-technical stakeholders. Manual conversion of these plans into three-dimensional (3D) models is time-consuming, expensive, and requires specialized expertise. This paper presents Skematix, an automated AI-based system that converts scanned or hand-drawn 2D floor plans into interactive 3D and augmented reality (AR) visualizations. The proposed approach integrates computer vision-based preprocessing with deep learning-driven semantic segmentation to detect architectural elements such as walls, doors, windows, and rooms. A structured 3D model is generated automatically using the Blender Python API and visualized through a browser-based WebXR interface. Experimental evaluation demonstrates that the system preserves spatial accuracy while significantly reducing modeling time and user effort. Skematix improves architectural communication, enhances design understanding, and provides an accessible visualization platform without requiring specialized CAD software.},
        keywords = {Augmented Reality, Computer Vision, Deep Learning, Floor Plan Analysis, Semantic Segmentation, 2D to 3D Conversion.},
        month = {January},
        }