PT-VTON: an Image-Based Virtual Try-On Network with Progressive Pose Attention Transfer

TL;DR

PT-VTON is a novel pose-transfer framework for virtual try-on that efficiently transfers clothing between images with arbitrary poses, maintaining detailed fabric and human appearance, and outperforms existing methods.

Contribution

Introduces PT-VTON, a pose-transfer-based virtual try-on system that handles arbitrary poses and shapes with minimal modifications to existing systems.

Findings

Outperforms other methods on quantitative metrics

Preserves detailed fabric and human appearance

Handles drastic pose variations effectively

Abstract

The virtual try-on system has gained great attention due to its potential to give customers a realistic, personalized product presentation in virtualized settings. In this paper, we present PT-VTON, a novel pose-transfer-based framework for cloth transfer that enables virtual try-on with arbitrary poses. PT-VTON can be applied to the fashion industry within minimal modification of existing systems while satisfying the overall visual fashionability and detailed fabric appearance requirements. It enables efficient clothes transferring between model and user images with arbitrary pose and body shape. We implement a prototype of PT-VTON and demonstrate that our system can match or surpass many other approaches when facing a drastic variation of poses by preserving detailed human and fabric characteristic appearances. PT-VTON is shown to outperform alternative approaches both on machine-based quantitative metrics and qualitative results.