Image-Based Virtual Try-On: A Survey

TL;DR

This survey comprehensively reviews current image-based virtual try-on techniques, analyzing methodologies, evaluation metrics, and future directions to bridge the gap between research and commercial applications.

Contribution

It provides a detailed overview of state-of-the-art methods, introduces a unified evaluation framework, and highlights unresolved issues to guide future research in virtual try-on.

Findings

Assessment of semantic alignment using CLIP

Evaluation of methods on a common dataset

Identification of key challenges and future directions

Abstract

Image-based virtual try-on aims to synthesize a naturally dressed person image with a clothing image, which revolutionizes online shopping and inspires related topics within image generation, showing both research significance and commercial potential. However, there is a gap between current research progress and commercial applications and an absence of comprehensive overview of this field to accelerate the development.In this survey, we provide a comprehensive analysis of the state-of-the-art techniques and methodologies in aspects of pipeline architecture, person representation and key modules such as try-on indication, clothing warping and try-on stage. We additionally apply CLIP to assess the semantic alignment of try-on results, and evaluate representative methods with uniformly implemented evaluation metrics on the same dataset.In addition to quantitative and qualitative evaluation of current open-source methods, unresolved issues are highlighted and future research directions are prospected to identify key trends and inspire further exploration. The uniformly implemented evaluation metrics, dataset and collected methods will be made public available at https://github.com/little-misfit/Survey-Of-Virtual-Try-On.