Abstract—In India, traditional saree stores frequently encounter challenges in providing fitting rooms, which impedes customers from confidently exploring saree options. This limitation stems from various factors, including space constraints within the stores and the intricate process of draping a saree, which can be time-consuming and challenging in a fitting room setting. Additionally, expanding the stores to accommodate fitting rooms may not always be feasible due to limitations in space or resources. As a result, customers often face difficulties assessing the fit and a high rate of returning the saree. Virtual dressing and leveraging immersive technologies revolutionize traditional shopping by integrating Augmented Reality (AR) and real-time Artificial Intelligence (AI). This paper addresses this challenge with an innovative method that combines AR and AI algorithms to integrate virtual sarees and simulate fabrics in real-time seamlessly. A smart mirror application has been developed in this research, functioning as a virtual dressing room. Positioned strategically, the mirror allows customers to effortlessly scan their measurements and use AR to virtually drape various saree styles, empowering them to make informed selections. The implementation results show that the proposed approach can enhance the in-store shopping experience and mitigate uncertainty associated with saree draping, providing a real-time, interactive reflection to boost confidence in offline saree selections. This innovative blend of technology and tradition transforms the saree shopping journey, bridging the virtual and physical realms for an enriched customer experience.
 
Keywords—augmented reality, artificial intelligence, virtual fitting room, smart mirror, virtual try-on, traditional shopping, saree draping


Copyright © 2025 by the authors. This 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 (CC BY 4.0).