Roop: An AI-Powered Virtual Try-On Platform
- DOI
- 10.2991/978-94-6239-650-0_22How to use a DOI?
- Keywords
- Virtual try-on; generative adversarial networks; computer vision; sustainable fashion; deep learning; mobile application; skin tone analysis; thrift verification
- Abstract
This project showcases ROOP, a mobile app that innovates the online fashion retail experience with features like AI-powered virtual try-on, personalized color analysis, and a thrift shopping experience focused on sustainability. The system consists of a three-stage deep learning pipeline that uses a U-Net model for body segmentation, a Geometric Matching Module for clothing warping, and attention-based synthesize clothing for photorealistic visualization of clothing fit. Skin tone classification achieved 94 percent accuracy utilizing Support Vector Machine and Random Forest classifiers to provide personalized color suggestions. The thrift market place uses Convolutional Neural Networks to verify the quality of second-hand garments in an automated way. Developed with React Native, users can upload images of themselves, visualize garments, and receive pre-authenticated thrift items through one interface.
- Copyright
- © 2026 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Siddhi P. Paradhi AU - Saniya Jitekar AU - Satyaja Shivthare AU - Gaurav Jha AU - Monika Bhagwat PY - 2026 DA - 2026/04/20 TI - Roop: An AI-Powered Virtual Try-On Platform BT - Proceedings of the Conference on Technologies for Future Cities (CTFC 2025) PB - Atlantis Press SP - 326 EP - 338 SN - 3005-155X UR - https://doi.org/10.2991/978-94-6239-650-0_22 DO - 10.2991/978-94-6239-650-0_22 ID - Paradhi2026 ER -