The paper aims to transfer the item image of a given clothing product to a corresponding area of the user image. Existing classical methods suffer from unconstrained deformation…
Abstract
Purpose
The paper aims to transfer the item image of a given clothing product to a corresponding area of the user image. Existing classical methods suffer from unconstrained deformation of clothing and occlusion caused by hair or poses, which leads to loss of details in the try-on results. In this paper, the authors present a details-oriented virtual try-on network (DO-VTON), which allows synthesizing high-fidelity try-on images with preserved characteristics of target clothing.
Design/methodology/approach
The proposed try-on network consists of three modules. The fashion parsing module (FPM) is designed to generate the parsing map of a reference person image. The geometric matching module (GMM) warps the input clothing and matches it with the torso area of the reference person guided by the parsing map. The try-on module (TOM) generates the final try-on image. In both FPM and TOM, attention mechanism is introduced to obtain sufficient features, which enhances the performance of characteristics preservation. In GMM, a two-stage coarse-to-fine training strategy with a grid regularization loss (GR loss) is employed to optimize the clothing warping.
Findings
In this paper, the authors propose a three-stage image-based virtual try-on network, DO-VTON, that aims to generate realistic try-on images with extensive characteristics preserved.
Research limitations/implications
The authors’ proposed algorithm can provide a promising tool for image based virtual try-on.
Practical implications
The authors’ proposed method is a technology for consumers to purchase favored clothes online and to reduce the return rate in e-commerce.
Originality/value
Therefore, the authors’ proposed algorithm can provide a promising tool for image based virtual try-on.
Details
Keywords
Jianchun Sun, Shiyong Yang, Shengping Huang, Zhijiang Shang and Weihao Ling
This paper addresses the issue of internal spatial environmental pollution in non-blasting tunnel construction by proposing a comprehensive evaluation model. The model aims to…
Abstract
Purpose
This paper addresses the issue of internal spatial environmental pollution in non-blasting tunnel construction by proposing a comprehensive evaluation model. The model aims to provide a scientific basis for environmental pollution prevention in non-blasting tunnel construction, thereby facilitating green tunnel construction and sustainable development management.
Design/methodology/approach
The study firstly refines and constructs the evaluation index system from the perspective of pollution sources. A novel weight calculation method is introduced by integrating the analytic hierarchy process (AHP) with the ordered weighted averaging (OWA) operator, and a comprehensive evaluation model for internal environmental pollution in non-blasting tunnels is established by incorporating the grey clustering evaluation method. Finally, an empirical study is conducted using the Erbaoshan Tunnel as a case study to verify the feasibility and effectiveness of the model.
Findings
The study develops an evaluation system for internal environmental pollution in non-blasting tunnels and applies it to the Erbaoshan Tunnel. The results classify the pollution level as “general pollution,” confirming the rationality and applicability of the evaluation system and model while also identifying the primary pollution factors.
Originality/value
This study first developed a comprehensive evaluation system for environmental pollution in non-blasting tunnel construction from the pollution source perspective, making the system more comprehensive. Additionally, it innovatively combined AHP–OWA and gray clustering methods to scientifically assess pollution levels, providing valuable scientific guidance for the evaluation and management of non-blasting tunnels and similar underground projects.