International Journal of Scientific Research and Engineering Development

The rapid expansion of e-commerce in the fashion industry has driven the development of Virtual Try-On (VTON) technologies, which enable consumers to visualize garments on their own bodies or representative avatars, enhancing the online shopping experience. This paper presents a comprehensive review and analysis of state-of-the-art VTON methods, including 2D image-based approaches such as CP-VTON and VITON, hybrid systems like CloTH-VTON, and fully 3D models exemplified by 3D-MPVTON. These techniques leverage advanced deep learning architectures—Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), Capsule Networks, and transformers—to achieve photorealistic garment fitting and synthesis.Our study highlights significant technical achievements, such as high segmentation accuracy and improved garment shape preservation, alongside commercial impacts including increased sales and reduced return rates. Despite these advancements, challenges remain in handling complex clothing textures, diverse body shapes, occlusion, and real-time performance constraints. Additionally, ethical considerations related to privacy and data quality demand attention.Future directions emphasize the integration of multimodal inputs, 3D pose estimation, and personalized styling, aiming to develop more inclusive, efficient, and scalable VTON systems. This research underscores the transformative potential of Virtual Try-On technologies in reshaping digital fashion retail by bridging the gap between physical and virtual shopping experiences.