SURVEY ON CONTEXT-DRIVEN IMAGE-BASED VIRTUAL TRY-ON NETWORK
International Research Journal of Modernization in Engineering Technology and Science · 2023
User-experience on fashion and clothing e-commerce websites can be enhanced with the help of Image-based virtual try-on techniques but, preexisting methods produce limited quality try-on results from input images In this paper author's propose a Context-Driven Virtual Try-On Network (C-VTON) which addresses these limitations and efficiently transfers desired clothing items on to the target subjects even under challenging poses and the presence of self-occlusions the proposed network consists of two components, (i) a geometric matching procedure that efficiently aligns the target clothing with the pose of the person in the input images, and (ii) a powerful image generator that utilizes various contextual information when synthesizing the final tryon result and produces a photo-realistic and convincing try-on result C-VTON has been tested against datasets like VITON and MPV and the results when compared with other state-of-the-art techniques found to be the most realistic and visually convincing significantly improves on the existing state-of-the-art.