WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Zijian, Chen, Peixin, Wang, Guangrun, Li, Guanbin, Torr, Philip H. S., Lin, Liang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929421245480960
author He, Zijian
Chen, Peixin
Wang, Guangrun
Li, Guanbin
Torr, Philip H. S.
Lin, Liang
author_facet He, Zijian
Chen, Peixin
Wang, Guangrun
Li, Guanbin
Torr, Philip H. S.
Lin, Liang
contents Video virtual try-on aims to generate realistic sequences that maintain garment identity and adapt to a person's pose and body shape in source videos. Traditional image-based methods, relying on warping and blending, struggle with complex human movements and occlusions, limiting their effectiveness in video try-on applications. Moreover, video-based models require extensive, high-quality data and substantial computational resources. To tackle these issues, we reconceptualize video try-on as a process of generating videos conditioned on garment descriptions and human motion. Our solution, WildVidFit, employs image-based controlled diffusion models for a streamlined, one-stage approach. This model, conditioned on specific garments and individuals, is trained on still images rather than videos. It leverages diffusion guidance from pre-trained models including a video masked autoencoder for segment smoothness improvement and a self-supervised model for feature alignment of adjacent frame in the latent space. This integration markedly boosts the model's ability to maintain temporal coherence, enabling more effective video try-on within an image-based framework. Our experiments on the VITON-HD and DressCode datasets, along with tests on the VVT and TikTok datasets, demonstrate WildVidFit's capability to generate fluid and coherent videos. The project page website is at wildvidfit-project.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2407_10625
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models
He, Zijian
Chen, Peixin
Wang, Guangrun
Li, Guanbin
Torr, Philip H. S.
Lin, Liang
Computer Vision and Pattern Recognition
Video virtual try-on aims to generate realistic sequences that maintain garment identity and adapt to a person's pose and body shape in source videos. Traditional image-based methods, relying on warping and blending, struggle with complex human movements and occlusions, limiting their effectiveness in video try-on applications. Moreover, video-based models require extensive, high-quality data and substantial computational resources. To tackle these issues, we reconceptualize video try-on as a process of generating videos conditioned on garment descriptions and human motion. Our solution, WildVidFit, employs image-based controlled diffusion models for a streamlined, one-stage approach. This model, conditioned on specific garments and individuals, is trained on still images rather than videos. It leverages diffusion guidance from pre-trained models including a video masked autoencoder for segment smoothness improvement and a self-supervised model for feature alignment of adjacent frame in the latent space. This integration markedly boosts the model's ability to maintain temporal coherence, enabling more effective video try-on within an image-based framework. Our experiments on the VITON-HD and DressCode datasets, along with tests on the VVT and TikTok datasets, demonstrate WildVidFit's capability to generate fluid and coherent videos. The project page website is at wildvidfit-project.github.io.
title WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.10625