ABSTRACT
The fashion industry is at the brink of radical transformation. The emergence of Artificial Intelligence (AI) in fashion applications creates many opportunities for this industry and make fashion a better space for everyone. Interesting to this matter, we proposed a virtual try-on interface to stimulate consumers purchase intentions and facilitate their online buying decision process. Thus, we present, in this paper, our flexible person generation system for virtual try-on that aiming to treat the task of human appearance transfer across images while preserving texture details and structural coherence of the generated outfit. This challenging task has drawn increasing attention and made huge development of intelligent fashion applications. However, it requires different challenges, especially in the case of a wide divergences between the source and target images. To solve this problem, we proposed a flexible person generation framework called Dress-up to treat the 2D virtual try-on task. Dress-up is an end-to-end generation pipeline with three modules based on the task of image-to-image translation aiming to sequentially interchange garments between images, and produce dressing effects not achievable by existing works. The core idea of our solution is to explicitly encode the body pose and the target clothes by a pre-processing module based on the semantic segmentation process. Then, a conditional adversarial network is implemented to generate target segmentation feeding respectively, to the alignment and translation networks to generate the final output results. The novelty of this work lies in realizing the appearance transfer across images with high quality by reconstructing garments on a person in different orders and looks from simlpy semantic maps and 2D images without using 3D modeling. Our system can produce dressing effects and provide significant results over the state-of-the-art methods on the widely used DeepFashion dataset. Extensive evaluations show that Dress-up outperforms other recent methods in terms of output quality, and handles a wide range of editing functions for which there is no direct supervision. Different types of results were computed to verify the performance of our proposed framework and show that the robustness and effectiveness are high by utilizing our method.
ABSTRACT
Since the last years and until now, technology has made fast progress for many industries, in particularly, garment industry which aims to follow consumer desires and demands. One of these demands is to fit clothes before purchasing them on-line. Therefore, many research works have been focused on how to develop an intelligent apparel industry to ensure the online shopping experience. Image-based virtual try-on is among the most potential approach of virtual fitting that tries on target clothes into customer's image, therefore, it has received considerable research efforts in the recent years. However, there are several challenges involved in development of virtual try-on that make it difficult to achieve naturally looking virtual outfit such as shape, pose, occlusion, illumination cloth texture, logo and text etc. The aim of this study is to provide a comprehensive and structured overview of extensive research on the advancement of virtual try-on. This review first introduces virtual try-on and its challenges followed by its demand in fashion industry. We summarize state-of-the-art image based virtual try-on for both fashion detection and fashion synthesis as well as their respective advantages, drawbacks, and guidelines for selection of specific try-on model followed by its recent development and successful application. Finally, we conclude the paper with promising directions for future research.
