PEMF-VTO: Point-Enhanced Video Virtual Try-on via Mask-free Paradigm

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chang, Tianyu, Chen, Xiaohao, Wei, Zhichao, Zhang, Xuanpu, Chen, Qing-Guo, Luo, Weihua, Song, Peipei, Yang, Xun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916850698289152
author Chang, Tianyu
Chen, Xiaohao
Wei, Zhichao
Zhang, Xuanpu
Chen, Qing-Guo
Luo, Weihua
Song, Peipei
Yang, Xun
author_facet Chang, Tianyu
Chen, Xiaohao
Wei, Zhichao
Zhang, Xuanpu
Chen, Qing-Guo
Luo, Weihua
Song, Peipei
Yang, Xun
contents Video Virtual Try-on aims to seamlessly transfer a reference garment onto a target person in a video while preserving both visual fidelity and temporal coherence. Existing methods typically rely on inpainting masks to define the try-on area, enabling accurate garment transfer for simple scenes (e.g., in-shop videos). However, these mask-based approaches struggle with complex real-world scenarios, as overly large and inconsistent masks often destroy spatial-temporal information, leading to distorted results. Mask-free methods alleviate this issue but face challenges in accurately determining the try-on area, especially for videos with dynamic body movements. To address these limitations, we propose PEMF-VTO, a novel Point-Enhanced Mask-Free Video Virtual Try-On framework that leverages sparse point alignments to explicitly guide garment transfer. Our key innovation is the introduction of point-enhanced guidance, which provides flexible and reliable control over both spatial-level garment transfer and temporal-level video coherence. Specifically, we design a Point-Enhanced Transformer (PET) with two core components: Point-Enhanced Spatial Attention (PSA), which uses frame-cloth point alignments to precisely guide garment transfer, and Point-Enhanced Temporal Attention (PTA), which leverages frame-frame point correspondences to enhance temporal coherence and ensure smooth transitions across frames. Extensive experiments demonstrate that our PEMF-VTO outperforms state-of-the-art methods, generating more natural, coherent, and visually appealing try-on videos, particularly for challenging in-the-wild scenarios. The link to our paper's homepage is https://pemf-vto.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2412_03021
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PEMF-VTO: Point-Enhanced Video Virtual Try-on via Mask-free Paradigm
Chang, Tianyu
Chen, Xiaohao
Wei, Zhichao
Zhang, Xuanpu
Chen, Qing-Guo
Luo, Weihua
Song, Peipei
Yang, Xun
Computer Vision and Pattern Recognition
Artificial Intelligence
Video Virtual Try-on aims to seamlessly transfer a reference garment onto a target person in a video while preserving both visual fidelity and temporal coherence. Existing methods typically rely on inpainting masks to define the try-on area, enabling accurate garment transfer for simple scenes (e.g., in-shop videos). However, these mask-based approaches struggle with complex real-world scenarios, as overly large and inconsistent masks often destroy spatial-temporal information, leading to distorted results. Mask-free methods alleviate this issue but face challenges in accurately determining the try-on area, especially for videos with dynamic body movements. To address these limitations, we propose PEMF-VTO, a novel Point-Enhanced Mask-Free Video Virtual Try-On framework that leverages sparse point alignments to explicitly guide garment transfer. Our key innovation is the introduction of point-enhanced guidance, which provides flexible and reliable control over both spatial-level garment transfer and temporal-level video coherence. Specifically, we design a Point-Enhanced Transformer (PET) with two core components: Point-Enhanced Spatial Attention (PSA), which uses frame-cloth point alignments to precisely guide garment transfer, and Point-Enhanced Temporal Attention (PTA), which leverages frame-frame point correspondences to enhance temporal coherence and ensure smooth transitions across frames. Extensive experiments demonstrate that our PEMF-VTO outperforms state-of-the-art methods, generating more natural, coherent, and visually appealing try-on videos, particularly for challenging in-the-wild scenarios. The link to our paper's homepage is https://pemf-vto.github.io/.
title PEMF-VTO: Point-Enhanced Video Virtual Try-on via Mask-free Paradigm
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.03021