Saved in:
Bibliographic Details
Main Authors: Xu, Zhengze, Chen, Mengting, Wang, Zhao, Xing, Linyu, Zhai, Zhonghua, Sang, Nong, Lan, Jinsong, Xiao, Shuai, Gao, Changxin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.17571
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914772099792896
author Xu, Zhengze
Chen, Mengting
Wang, Zhao
Xing, Linyu
Zhai, Zhonghua
Sang, Nong
Lan, Jinsong
Xiao, Shuai
Gao, Changxin
author_facet Xu, Zhengze
Chen, Mengting
Wang, Zhao
Xing, Linyu
Zhai, Zhonghua
Sang, Nong
Lan, Jinsong
Xiao, Shuai
Gao, Changxin
contents Video try-on is a challenging task and has not been well tackled in previous works. The main obstacle lies in preserving the details of the clothing and modeling the coherent motions simultaneously. Faced with those difficulties, we address video try-on by proposing a diffusion-based framework named "Tunnel Try-on." The core idea is excavating a "focus tunnel" in the input video that gives close-up shots around the clothing regions. We zoom in on the region in the tunnel to better preserve the fine details of the clothing. To generate coherent motions, we first leverage the Kalman filter to construct smooth crops in the focus tunnel and inject the position embedding of the tunnel into attention layers to improve the continuity of the generated videos. In addition, we develop an environment encoder to extract the context information outside the tunnels as supplementary cues. Equipped with these techniques, Tunnel Try-on keeps the fine details of the clothing and synthesizes stable and smooth videos. Demonstrating significant advancements, Tunnel Try-on could be regarded as the first attempt toward the commercial-level application of virtual try-on in videos.
format Preprint
id arxiv_https___arxiv_org_abs_2404_17571
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Tunnel Try-on: Excavating Spatial-temporal Tunnels for High-quality Virtual Try-on in Videos
Xu, Zhengze
Chen, Mengting
Wang, Zhao
Xing, Linyu
Zhai, Zhonghua
Sang, Nong
Lan, Jinsong
Xiao, Shuai
Gao, Changxin
Computer Vision and Pattern Recognition
Video try-on is a challenging task and has not been well tackled in previous works. The main obstacle lies in preserving the details of the clothing and modeling the coherent motions simultaneously. Faced with those difficulties, we address video try-on by proposing a diffusion-based framework named "Tunnel Try-on." The core idea is excavating a "focus tunnel" in the input video that gives close-up shots around the clothing regions. We zoom in on the region in the tunnel to better preserve the fine details of the clothing. To generate coherent motions, we first leverage the Kalman filter to construct smooth crops in the focus tunnel and inject the position embedding of the tunnel into attention layers to improve the continuity of the generated videos. In addition, we develop an environment encoder to extract the context information outside the tunnels as supplementary cues. Equipped with these techniques, Tunnel Try-on keeps the fine details of the clothing and synthesizes stable and smooth videos. Demonstrating significant advancements, Tunnel Try-on could be regarded as the first attempt toward the commercial-level application of virtual try-on in videos.
title Tunnel Try-on: Excavating Spatial-temporal Tunnels for High-quality Virtual Try-on in Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.17571