Search results

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.

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.

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.

The authors’ proposed algorithm can provide a promising tool for image based virtual try-on.

The authors’ proposed method is a technology for consumers to purchase favored clothes online and to reduce the return rate in e-commerce.

Therefore, the authors’ proposed algorithm can provide a promising tool for image based virtual try-on.

The purpose of this paper is to understand how augmented reality (AR) try-on experiences facilitate consumers’ shopping decision. Focusing on the immersion and psychological ownership, the study investigated how the properties of AR experiences (environmental embedding (EE) and simulated physical control (SPC)) affect decision comfort.

This research theoretically and empirically analyzes how each property of AR experiences affects consequential psychological states and then further increases decision comfort by employing an existing AR try-on mobile application. A total of 99 valid responses were used for the partial least square structural equation modeling analysis. One’s prior AR try-on experience was predicted as a moderator and analyzed using SPSS-based PROCESS macro.

The results demonstrated that EE and SPC evoke immersion and the feeling of ownership of a virtual product, which increased decision comfort. The moderating effect of one’s prior AR try-on experience showed that the impact of EE and SPC on immersion was attenuated for those with prior experience. Further, immersion mediated the effect of EE but SPC on the feeling of ownership, which corroborated the direct effect of SPC on the feeling of ownership.

Firms must consider technological and user-experience features that can induce users to perceive high levels of AR characteristics such as EE and SPC. Practitioners should develop realistic content that can correctly place virtual products on users to enhance EE. Including more interactive features is encouraged to provide users with a feeling of control toward the virtual product that directly leads to ownership and positively affects decision making. Further, practitioners need to be cautious about consumers getting used to the new technology; retailers and marketers need to focus on creating new and innovative content to continually engage customers.

This study adopted EE and SPC to determine how each property of AR experience forms the consequential psychological states, particularly depending on one’s prior experience. Methodologically, the study provided external validity in conducting an experiment by adopting an existing AR mobile application available in the market and employing an objective measure of respondents (e.g. prior AR try-on experience).

Nowadays, artificial intelligence (AI) technology has demonstrated extensive applications in the field of art design. Attribute editing is an important means to realize clothing style and color design via computer language, which aims to edit and control the garment image based on the specified target attributes while preserving other details from the original image. The current image attribute editing model often generates images containing missing or redundant attributes. To address the problem, this paper aims for a novel design method utilizing the Fashion-attribute generative adversarial network (AttGAN) model was proposed for image attribute editing specifically tailored to women’s blouses.

The proposed design method primarily focuses on optimizing the feature extraction network and loss function. To enhance the feature extraction capability of the model, an increase in the number of layers in the feature extraction network was implemented, and the structure similarity index measure (SSIM) loss function was employed to ensure the independent attributes of the original image were consistent. The characteristic-preserving virtual try-on network (CP_VTON) dataset was used for train-ing to enable the editing of sleeve length and color specifically for women’s blouse.

The experimental results demonstrate that the optimization model’s generated outputs have significantly reduced problems related to missing attributes or visual redundancy. Through a comparative analysis of the numerical changes in the SSIM and peak signal-to-noise ratio (PSNR) before and after the model refinement, it was observed that the improved SSIM increased substantially by 27.4%, and the PSNR increased by 2.8%, serving as empirical evidence of the effectiveness of incorporating the SSIM loss function.

The proposed algorithm provides a promising tool for precise image editing of women’s blouses based on the GAN. This introduces a new approach to eliminate semantic expression errors in image editing, thereby contributing to the development of AI in clothing design.

Existing clothing parsing methods make little use of dataset-level information. This paper aims to propose a novel clothing parsing method which utilizes higher-level outfit combinatorial consistency knowledge from the whole clothing dataset to improve the accuracy of segmenting clothing images.

In this paper, the authors propose an Outfit Memory Net (OMNet) that augments original feature by aggregating dataset-level prior clothing combination information. Specifically, the authors design an Outfit Matrix (OM) to represent clothing combination information of single image and an Outfit Memory Module (OMM) to store the clothing combination information of all images in the training set, i.e. dataset-level clothing combination information. In addition, the authors propose a Multi-scale Aggregation Module (MAM) to aggregate the clothing combination information in a multi-scale manner to solve the problem of large variance in the scale of objects in the clothing images.

Experiments on Colorful Fashion Parsing Dataset (CFPD) dataset show that the authors' method achieves 93.15% pixel accuracy (PA) and 51.24% mean of class-wise intersection over union (mIoU), which are satisfactory parsing results compared with existing methods such as PSPNet, DANet and DeepLabV3. Moreover, through comparing the segmentation accuracy of different methods for each category, MAM could effectively improve the segmentation of small objects.

With the rise of various online shopping platforms and the continuous development of deep learning technology, emerging applications such as clothing recommendation, matching, classification and virtual try-on system have emerged in the clothing field. Clothing parsing is the key technology to realize these applications. Therefore, improving the accuracy of clothing parsing is necessary.

One of the main challenges that brands face is the ability to provide a real-life experience through online platforms. The aim of this study is to analyze consumers' self-concept and testimonials through an augmented reality (AR) try-on app versus a website.

An online survey was conducted with 222 participants, in which they were randomly exposed to two scenarios: AR try-on app or website experience and positive versus negative reviews presence.

The findings indicate positive effects of ideal self-congruence on purchase intention and confidence in fit. Low self-esteem consumers experience greater ideal self-congruence using AR when compared to the website. Confidence in fit partially mediates between ideal self-congruence and purchase intention. Higher levels of diagnosticity of reviews conduct to higher levels of purchase intention.

This study contributes to interactive marketing by exploring the effect of appearance self-esteem in the relationship between AR app versus website and ideal self-congruence and how this influences consumer behavior. In addition, the study also emphasizes the role of testimonials in shaping consumer intentions.

This study aimed to clarify the criteria for subjective evaluation of the similarities and differences between virtual and actual pants and propose a quantitative evaluation method for those similarities and differences based on geometric features related to the evaluation.

Using patterns, we made five pairs of actual pants for a dummy in five fabrics. We simulated virtual pants with a 3-D simulator. Sensory evaluation was conducted with images of the virtual and actual pants: 20 participants compared the images based on a questionnaire. For the structure of evaluation, the authors undertook analysis of variance and principal component analysis. The actual and virtual pants were geometrically compared using the 3-D scanned data. To investigate the relationship between quantitative and sensory evaluation, the authors calculated the correlation coefficients.

The authors found that subjects perceived the differences between actual and simulated pants. When comparing the virtual and actual pants, the criteria for the differences were the silhouette from the front view, hem width, waist and wrinkles. Using differences in the hem width, it would be possible to evaluate the differences between actual and simulated pants. Roughness and smoothness of the silhouette also affected evaluation.

The authors clarified the evaluation criteria for the similarities and differences between virtual and actual pants. The authors proposed a quantitative evaluation method for the similarities and differences between virtual and actual garment based on our criteria. This study will be of benefit to 3-D simulator users and developers.

Augmented reality (AR) integrates the digital world with the real world and thus, provides a real-time experience to the users. With AR, the immediate surroundings become a learning platform for the users. The perception of the products has been enhanced many times with AR; thus, enriching user experience and responsiveness. The purpose of this paper is to bring forth the basics of AR and provide an overview of the research work carried out by researchers in the implementation of AR in different sectors.

This paper summarizes the usefulness of AR in different industries. The authors have identified the peer-reviewed research publications from Web of Science, Scopus, Google Scholar, etc. The selection of literature has been made based upon the significance of AR in recent times. The industries/sectors where AR has been implemented successfully have been considered for this paper. The paper has been divided into various sections and subsections to bring more clarity to the readers.

This paper presents a brief and a precise information on Industry 4.0 and AR. The basic working of AR system and its implications have also been discussed. The preference of AR over virtual reality (VR) has also been deliberated in this paper. The authors have presented the usefulness of AR in different sectors such as smart factories, ship yard building, online shopping, surgery and education. This paper discusses the AR-ready procedures being followed in these sectors.

AR has been an add-on to VR systems. The processes in industries have become very handy and informative with AR. Because the application of AR in different sectors has not been discussed in a single paper; thus, this work presents a systematic literature review on the applications of AR in different sectors/industries.

Accurate and automatic clothing pattern making is very important in personalized clothing customization and virtual fitting room applications. Clothing pattern generating as well as virtual clothing simulation is an attractive research issue both in clothing industry and computer graphics.

Physics-based method is an effective way to model dynamic process and generate realistic clothing animation. Due to conceptual simplicity and computational speed, mass-spring model is frequently used to simulate deformable and soft objects follow the natural physical rules. We present a physics-based clothing pattern generating framework by using scanned human body model. After giving a scanned human body model, first, we extract feature points, planes and curves on the 3D model by geometric analysis, and then, we construct a remeshed surface which has been formatted to connected quad meshes. Second, for each clothing piece in 3D, we construct a mass-spring model with same topological structures, and conduct a typical time integration algorithm to the mass-spring model. Finally, we get the convergent clothing pieces in 2D of all clothing parts, and we reconnected parts which are adjacent on 3D model to generate the basic clothing pattern.

The results show that the presented method is a feasible way for clothing pattern generating by use of scanned human body model.

The main contribution of this work is twofold: one is the geometric algorithm to scanned human body model, which is specially conducted for clothing pattern design to extract feature points, planes and curves. This is the crucial base for suit clothing pattern generating. Another is the physics-based pattern generating algorithm which flattens the 3D shape to 2D shape of cloth pattern pieces.

In recent years, there has been significant interest in adopting XR (extended reality) technologies such as VR (virtual reality) and AR (augmented reality), particularly in retail. However, extending activities through reality-mediation is still mostly believed to offer an inferior experience due to their shortcomings in usability, wearability, graphical fidelity, etc. This study aims to address the research gap by experimentally examining the acceptance of metaverse shopping.

This study conducts a 2 (VR: with vs. without) × 2 (AR: with vs. without) between-subjects laboratory experiment involving 157 participants in simulated daily shopping environments. This study builds a physical brick-and-mortar store at the campus and stocked it with approximately 600 products with accompanying product information and pricing. The XR devices and a 3D laser scanner were used in constructing the three XR shopping conditions.

Results indicate that XR can offer an experience comparable to, or even surpassing, traditional shopping in terms of its instrumental and hedonic aspects, regardless of a slightly reduced perception of usability. AR negatively affected perceived ease of use, while VR significantly increased perceived enjoyment. It is surprising that the lower perceived ease of use appeared to be disconnected from the attitude toward metaverse shopping.

This study provides important experimental evidence on the acceptance of XR shopping, and the finding that low perceived ease of use may not always be detrimental adds to the theory of technology adoption as a whole. Additionally, it provides an important reference point for future randomized controlled studies exploring the effects of technology on adoption.

This study aims to investigate the influence of different virtual fashion styles on attitude and satisfaction within virtual reality (VR) tourism experiences. The investigation considers the mediating effect of perceived attractiveness, popularity, novelty and weirdness, as well as the moderating role of self-congruence with avatar clothing and the desire for unique products.

This research uses a quantitative experimental approach. Initially, a three-step pilot study (N = 201) was conducted to select avatar fashion styles for the main investigation. In the primary study, participants (N = 326) engaged with one out of four fashion style conditions to select attire for their avatars and then completed a self-administered survey. Data analysis involved paired-sample t-tests, multivariate analysis of variance and Hayes’ PROCESS Models.

The results show that presenting fantasy avatar fashion styles leads to a decrease in perceived attractiveness and popularity, while concurrently increasing perceptions of novelty and weirdness which in turn exert a negative influence on attitude and satisfaction with the virtual fitting room (VFR). However, these relationships change when considering the moderating role of self-congruence with avatar clothing and the desire for unique products.

VR tourism experience providers and designers can use research findings to bolster positive attitude and enhance satisfaction with VFR; an important first step that strongly affects the rest of the VR tourist journey.

This study contributes to tourism research by exploring the intersection of immersive technologies and virtual fashion. It emphasizes the enhancement of critical touchpoints like the VFR, moving beyond a sole focus on VR adoption, to improve the overall virtual tourist experience.