Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Ben, Li, Minqi, Ren, Jie, Zhang, Kaibing
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.23439
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915312600875008
author Li, Ben
Li, Minqi
Ren, Jie
Zhang, Kaibing
author_facet Li, Ben
Li, Minqi
Ren, Jie
Zhang, Kaibing
contents Image-based virtual try-on aims to fit a target garment to a specific person image and has attracted extensive research attention because of its huge application potential in the e-commerce and fashion industries. To generate high-quality try-on results, accurately warping the clothing item to fit the human body plays a significant role, as slight misalignment may lead to unrealistic artifacts in the fitting image. Most existing methods warp the clothing by feature matching and thin-plate spline (TPS). However, it often fails to preserve clothing details due to self-occlusion, severe misalignment between poses, etc. To address these challenges, this paper proposes a detail retention virtual try-on method via accurate non-rigid registration (VITON-DRR) for diverse human poses. Specifically, we reconstruct a human semantic segmentation using a dual-pyramid-structured feature extractor. Then, a novel Deformation Module is designed for extracting the cloth key points and warping them through an accurate non-rigid registration algorithm. Finally, the Image Synthesis Module is designed to synthesize the deformed garment image and generate the human pose information adaptively. {Compared with} traditional methods, the proposed VITON-DRR can make the deformation of fitting images more accurate and retain more garment details. The experimental results demonstrate that the proposed method performs better than state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23439
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VITON-DRR: Details Retention Virtual Try-on via Non-rigid Registration
Li, Ben
Li, Minqi
Ren, Jie
Zhang, Kaibing
Computer Vision and Pattern Recognition
Image-based virtual try-on aims to fit a target garment to a specific person image and has attracted extensive research attention because of its huge application potential in the e-commerce and fashion industries. To generate high-quality try-on results, accurately warping the clothing item to fit the human body plays a significant role, as slight misalignment may lead to unrealistic artifacts in the fitting image. Most existing methods warp the clothing by feature matching and thin-plate spline (TPS). However, it often fails to preserve clothing details due to self-occlusion, severe misalignment between poses, etc. To address these challenges, this paper proposes a detail retention virtual try-on method via accurate non-rigid registration (VITON-DRR) for diverse human poses. Specifically, we reconstruct a human semantic segmentation using a dual-pyramid-structured feature extractor. Then, a novel Deformation Module is designed for extracting the cloth key points and warping them through an accurate non-rigid registration algorithm. Finally, the Image Synthesis Module is designed to synthesize the deformed garment image and generate the human pose information adaptively. {Compared with} traditional methods, the proposed VITON-DRR can make the deformation of fitting images more accurate and retain more garment details. The experimental results demonstrate that the proposed method performs better than state-of-the-art methods.
title VITON-DRR: Details Retention Virtual Try-on via Non-rigid Registration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.23439