Related papers: Better Fit: Accommodate Variations in Clothing Types for Virtual Try-on

Better Fit: Accommodate Variations in Clothing Types for Virtual Try-on

URL: http://arxiv.org/abs/2403.08453v1
Date: Wed, 13 Mar 2024 12:07:14 GMT
Title: Better Fit: Accommodate Variations in Clothing Types for Virtual Try-on
Authors: Xuanpu Zhang and Dan Song and Pengxin Zhan and Qingguo Chen and Kuilong Liu and Anan Liu
Abstract summary: Image-based virtual try-on aims to transfer target in-shop clothing to a dressed model image. We propose an adaptive mask training paradigm that dynamically adjusts training masks. For unpaired try-on validation, we construct a comprehensive cross-try-on benchmark.
Score: 25.550019373321653
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Image-based virtual try-on aims to transfer target in-shop clothing to a dressed model image, the objectives of which are totally taking off original clothing while preserving the contents outside of the try-on area, naturally wearing target clothing and correctly inpainting the gap between target clothing and original clothing. Tremendous efforts have been made to facilitate this popular research area, but cannot keep the type of target clothing with the try-on area affected by original clothing. In this paper, we focus on the unpaired virtual try-on situation where target clothing and original clothing on the model are different, i.e., the practical scenario. To break the correlation between the try-on area and the original clothing and make the model learn the correct information to inpaint, we propose an adaptive mask training paradigm that dynamically adjusts training masks. It not only improves the alignment and fit of clothing but also significantly enhances the fidelity of virtual try-on experience. Furthermore, we for the first time propose two metrics for unpaired try-on evaluation, the Semantic-Densepose-Ratio (SDR) and Skeleton-LPIPS (S-LPIPS), to evaluate the correctness of clothing type and the accuracy of clothing texture. For unpaired try-on validation, we construct a comprehensive cross-try-on benchmark (Cross-27) with distinctive clothing items and model physiques, covering a broad try-on scenarios. Experiments demonstrate the effectiveness of the proposed methods, contributing to the advancement of virtual try-on technology and offering new insights and tools for future research in the field. The code, model and benchmark will be publicly released.