NL-VTON: a non-local virtual try-on network with feature preserving of body and clothes

In an image based virtual try-on network, both features of the target clothes and the input human body should be preserved. However, current techniques failed to solve the problems of blurriness on complex clothes details and artifacts on human body occlusion regions at the same time. To tackle this...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2021-10, Vol.11 (1), p.19950-19950, Article 19950
Main Authors: Tan, Ze Lin, Bai, Jing, Zhang, Shao Min, Qin, Fei Wei
Format: Article
Language:English
Subjects:
639/705/117
639/705/258
Computer science
Convolution
Design
Fashion models
Human body
Humanities and Social Sciences
Methods
multidisciplinary
Occlusion
Receptive field
Science
Science (multidisciplinary)
Segmentation
Semantics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In an image based virtual try-on network, both features of the target clothes and the input human body should be preserved. However, current techniques failed to solve the problems of blurriness on complex clothes details and artifacts on human body occlusion regions at the same time. To tackle this issue, we propose a non-local virtual try-on network NL-VTON. Considering that convolution is a local operation and limited by its convolution kernel size and rectangular receptive field, which is unsuitable for large size non-rigid transformations of persons and clothes in virtual try-on, we introduce a non-local feature attention module and a grid regularization loss so as to capture detailed features of complex clothes, and design a human body segmentation prediction network to further alleviate the artifacts on occlusion regions. The quantitative and qualitative experiments based on the Zalando dataset demonstrate that our proposed method significantly improves the ability to preserve features of bodies and clothes compared with the state-of-the-art methods.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-021-99406-6