Saved in:
Bibliographic Details
Main Authors: Fang, Zixun, Zhai, Wei, Su, Aimin, Song, Hongliang, Zhu, Kai, Wang, Mao, Chen, Yu, Liu, Zhiheng, Cao, Yang, Zha, Zheng-Jun
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.11794
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913365602861056
author Fang, Zixun
Zhai, Wei
Su, Aimin
Song, Hongliang
Zhu, Kai
Wang, Mao
Chen, Yu
Liu, Zhiheng
Cao, Yang
Zha, Zheng-Jun
author_facet Fang, Zixun
Zhai, Wei
Su, Aimin
Song, Hongliang
Zhu, Kai
Wang, Mao
Chen, Yu
Liu, Zhiheng
Cao, Yang
Zha, Zheng-Jun
contents Video virtual try-on aims to transfer a clothing item onto the video of a target person. Directly applying the technique of image-based try-on to the video domain in a frame-wise manner will cause temporal-inconsistent outcomes while previous video-based try-on solutions can only generate low visual quality and blurring results. In this work, we present ViViD, a novel framework employing powerful diffusion models to tackle the task of video virtual try-on. Specifically, we design the Garment Encoder to extract fine-grained clothing semantic features, guiding the model to capture garment details and inject them into the target video through the proposed attention feature fusion mechanism. To ensure spatial-temporal consistency, we introduce a lightweight Pose Encoder to encode pose signals, enabling the model to learn the interactions between clothing and human posture and insert hierarchical Temporal Modules into the text-to-image stable diffusion model for more coherent and lifelike video synthesis. Furthermore, we collect a new dataset, which is the largest, with the most diverse types of garments and the highest resolution for the task of video virtual try-on to date. Extensive experiments demonstrate that our approach is able to yield satisfactory video try-on results. The dataset, codes, and weights will be publicly available. Project page: https://becauseimbatman0.github.io/ViViD.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11794
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ViViD: Video Virtual Try-on using Diffusion Models
Fang, Zixun
Zhai, Wei
Su, Aimin
Song, Hongliang
Zhu, Kai
Wang, Mao
Chen, Yu
Liu, Zhiheng
Cao, Yang
Zha, Zheng-Jun
Computer Vision and Pattern Recognition
Video virtual try-on aims to transfer a clothing item onto the video of a target person. Directly applying the technique of image-based try-on to the video domain in a frame-wise manner will cause temporal-inconsistent outcomes while previous video-based try-on solutions can only generate low visual quality and blurring results. In this work, we present ViViD, a novel framework employing powerful diffusion models to tackle the task of video virtual try-on. Specifically, we design the Garment Encoder to extract fine-grained clothing semantic features, guiding the model to capture garment details and inject them into the target video through the proposed attention feature fusion mechanism. To ensure spatial-temporal consistency, we introduce a lightweight Pose Encoder to encode pose signals, enabling the model to learn the interactions between clothing and human posture and insert hierarchical Temporal Modules into the text-to-image stable diffusion model for more coherent and lifelike video synthesis. Furthermore, we collect a new dataset, which is the largest, with the most diverse types of garments and the highest resolution for the task of video virtual try-on to date. Extensive experiments demonstrate that our approach is able to yield satisfactory video try-on results. The dataset, codes, and weights will be publicly available. Project page: https://becauseimbatman0.github.io/ViViD.
title ViViD: Video Virtual Try-on using Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.11794