ClothFit: Cloth-Human-Attribute Guided Virtual Try-On Network Using 3D Simulated Dataset

TL;DR

ClothFit is a novel virtual try-on system that predicts clothing draping on a human model by considering body proportions and clothing sizes, leading to more realistic online apparel visualization.

Contribution

This paper introduces ClothFit, a U-Net-based model that integrates human attributes and clothing sizes for improved virtual try-on realism, addressing limitations of prior methods.

Findings

Outperforms existing methods in photo-realism

Effectively incorporates body proportions and clothing sizes

Enhances online clothing shopping experience

Abstract

Online clothing shopping has become increasingly popular, but the high rate of returns due to size and fit issues has remained a major challenge. To address this problem, virtual try-on systems have been developed to provide customers with a more realistic and personalized way to try on clothing. In this paper, we propose a novel virtual try-on method called ClothFit, which can predict the draping shape of a garment on a target body based on the actual size of the garment and human attributes. Unlike existing try-on models, ClothFit considers the actual body proportions of the person and available cloth sizes for clothing virtualization, making it more appropriate for current online apparel outlets. The proposed method utilizes a U-Net-based network architecture that incorporates cloth and human attributes to guide the realistic virtual try-on synthesis. Specifically, we extract features from a cloth image using an auto-encoder and combine them with features from the user's height, weight, and cloth size. The features are concatenated with the features from the U-Net encoder, and the U-Net decoder synthesizes the final virtual try-on image. Our experimental results demonstrate that ClothFit can significantly improve the existing state-of-the-art methods in terms of photo-realistic virtual try-on results.