Search

PurposeThe 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/approachThe 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.FindingsIn 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/implicationsThe authors’ proposed algorithm can provide a promising tool for image based virtual try-on.Practical implicationsThe authors’ proposed method is a technology for consumers to purchase favored clothes online and to reduce the return rate in e-commerce.Originality/valueTherefore, the authors’ proposed algorithm can provide a promising tool for image based virtual try-on.

In this paper, the problem of inferring fabric mechanical properties based on three-dimensional (3D) fabric drape model and fabric weight was studied. Firstly, the three-dimensional point cloud of ...

In order to generate the three-dimensional (3D) mesh of draped fabric based on a two-dimensional (2D) fabric projection, the 3D point cloud of draped fabric was scanned via a self-built 3D scanning...

In the apparel manufacturing, the fabric is the single largest element in the cost of the garment. Therefore, effectual fabric consumption causes a reduction in cost and exertions. The purpose of this research is to study the effects of fabric width on the efficiency of marker (cutting) plans. Fabric consumption is in four types for human body shapes, that is, triangle, oval, square, and circle, in both genders to control the fabric utilization. Two clothing styles, fitted trousers and fitted shirts, are manufactured in an apparel manufacturing industry. The marker plans produced through Garment Gerber Technology software are accomplished in 36 different fabric widths (independent variables). The evaluation of dependent variables, that is, marker efficiency, marker loss, and fabric consumption efficiency relevant to four body shapes in variable fabric widths is analyzed for both women and men. The statistical analysis indicates that there is a linear relationship between marker efficiency and fabric width (sig

Advanced wearable medical devices are widely used for health monitoring, i.e. recording and analyzing signals from human organs. However, the signal quality is influenced significantly by medical e...

This study aims to develop a novel wearable electrode which has better moisture comfort and improves the stability of electrical signal monitoring. The silver-plated filaments were chlorinated by t...

Fabric quality and performance is assessed subjectively by the customer using an important and complex phenomenon of fabric hand. Objectively, it is evaluated with complicated and expensive instruments, such as Kawabata Evaluation System for Fabrics (KES-F) and Fabric Assurance with Simple Testing (FAST). The present research explores a non-touch objective approach, i.e., three-dimensional (3D) drape model to estimate fabric hand. Fabric hand prediction was testified on different commercial fabrics spanning a wide range of areal weight, thickness, yarn count, and fabric density. Fabric objective ranks based on drape indicators using principal component analysis (PCA) were compared with subjective ranks of fabric hand. Additionally, fabric drape is evaluated three dimensionally and a new drape indicator drape height (DH) is proposed. The cosine similarity results have proved fabric drape as an objective alternate to fabric hand.

In this paper, we present a novel non-parametric method for precisely reconstructing a three dimensional (3D) virtual mannequin from anthropometric measurements and mask image(s) based on Graph Convolution Network (GCN). The proposed method avoids heavy dependence on a particular parametric body model such as SMPL or SCPAE and can predict mesh vertices directly, which is significantly more comfortable using a GCN than a typical Convolutional Neural Network (CNN). To further improve the accuracy of the reconstruction and make the reconstruction more controllable, we incorporate the anthropometric measurements into the developed GCN. Our non-parametric reconstruction results distinctly outperform the previous graph convolution method, both visually and in terms of anthropometric accuracy. We also demonstrate that the proposed network possesses the capability to reconstruct a plausible 3D mannequin from a single-view mask. The proposed method can be effortless extended to a parametric method by appending a Multilayer Perception (MLP) to regress the parametric space of the Principal Component Analysis (PCA) model to achieve 3D reconstruction as well. Extensive experimental results demonstrate that our anthropometric GCN itself is very useful in improving the reconstruction accuracy, and the proposed method is effective and robust for 3D mannequin reconstruction.

To evaluate the ability of woven fabrics to drape in a more accurate way, a three-dimensional point cloud of a draped woven fabric was captured via an in-house drape-scanner. A new indicator, total drape angle (TDA), was proposed based on the three-dimensional fabric drape to characterize the ability of a woven fabric to drape. The relationship between TDA and the drape coefficient (DC) was analyzed to validate the performance of TDA. The result indicated that TDA is more stable and representative than the traditional DC in characterizing the ability of a woven fabric to drape. In addition, the drape angle distribution function (DADF) of the triangular mesh was employed to describe fabric drape, as well as to bridge the gap between drape configuration and the warp bending rigidity of woven fabric. The results showed that the correlation coefficient between the real warp bending rigidity value and what was predicted warp based on DADF and fabric weight was 0.952.

The 3D virtual mannequin has been widely used in apparel industry, and its importance is also increasing. This work develops a new 3D virtual mannequin reconstruction system based on optimization. All the mannequins reconstructed by the proposed approach share the identical topology, that is, there is a point-to-point correspondence among the mannequins, which will significantly facilitate much subsequent processing in fashion design, made-to-measure, and virtual try-on. The inputs to the proposed system contain a template human body, a raw scan (represented in mesh), and a very sparse corresponding landmarks set. The proposed approach substantially utilizes the optimization technology to drive the template to deform into a real scan. There is no special requirement on the raw meshes. The raw meshes may have a different number of vertices and triangles or may even be incomplete. The proposed method only needs 21 landmarks as hard-constraints to reconstruct a mannequin with tens of thousands of vertices. These landmarks can be extracted automatically for standard mannequin reconstruction. Besides the standard mannequin, the proposed system can also be used to reconstruct display mannequins, that is, mannequins with various poses. The experiments visualize the optimization procedure and verify that the optimization is efficient and effective. Quantitative analysis also proves that the reconstruction error satisfies the requirements of fashion design and tailoring.

In this article, a theoretical model of resistive network for woven conductive fabric is proposed to compute the resistance in warp and weft direction respectively. In order to enhance the accuracy...

In the apparel manufacturing, fabric utilization always remains the significant apprehensions in controlling the production expenditure. Alteration in pattern shapes and marker preparation leads to the enormous utilization of fabric. The purpose of this research is to study fabric efficiency in correspondence with four different human body shapes in both genders. Two clothing styles, fitted trousers and fitted shirts, were processed conventionally in the garment manufacturing company. The comparative study of auto-marker and manual-marker making through Garment Gerber Technology (GGT) software were also accomplished. The evaluation of fabric consumptions, marker efficiency, marker loss, fabric loss, and fabric cost relevant to four different body shapes was analyzed for both women and men. The investigation carried out in this article concludes that there are differences in fabric consumptions, efficiencies, and cost-effectiveness relative to body shapes. The result revealed that the manualmarker of trousers for triangular body shape in women’s wears has the least fabric consumption (most cost-effective), whereas the shirt’s auto-marker for an oval body shape in men’s wears has the most fabric utilization (least costeffective). The manual-virtual-marker making is efficient (significant p-value) than auto-generated-markers. Also, fabric utilization for women’s garments is cost-effective than that for men. Trousers are cost-effective compared to the shirts.

Image-based garment transfer systems aim to swap the desired clothes from a model to arbitrary users. However, existing works cannot provide the capacity for users to try on various fashion articles according to their wishes, i.e., users can decide which article (e.g., tops, pants or both) to be swapped. In this paper, we propose an Inpainting-based Virtual Try-On Network (I-VTON) which allows the user to try on arbitrary clothes from the model image in a selective manner. To realize the selectivity, we reshape the virtual try-on as a task of image inpainting. Firstly, the texture from the garment and the user are extracted respectively to form a coarse result. In this phase, users can decide which clothes they hope to try on via an interactive texture control mechanism. Secondly, the missing regions in the coarse result are recovered via a Texture Inpainting Network (TIN). We introduce a triplet training strategy to ensure the naturalness of the final result. Qualitative and quantitative experimental results demonstrate that I-VTON outperforms the state-of-the-art methods on both the garment details and the user identity. It is also confirmed our approach can flexibly transfer the clothes in a selective manner.

In apparel manufacturing, more than 50 % cost is consumed by the textile fabric. Therefore companies have significant apprehensions in the fabric utilization. It can result in more efficient and cost-effective in fabric utilization if they are related to different body shapes. The purpose of this study is to classify female body shapes and evaluate fabric utilization efficiency for each category of the body shape. To this end, three dimensional (3D) body scans are collected from 124 young female subjects. For the body shape analysis, 3D body scans are processed by using Moore neighbor algorithm and region prop function to perceive the outermost shell. Moreover, both front and side view of the scans is processed for data reduction using Principle Component Analysis (PCA) and clustering using K-Means ++. It has been observed through our analysis of a dataset that female bodies can be categorized into four body shapes, that is, oval shape, circle shape, triangle shape, and rectangle shape. It has also been observed that all four body shape categories exhibit dissimilar anthropometric size measures. The result implies that these body shapes have devoured different fabric utilization for the garments (fitted trouser and fitted shirt). It has been noted that in fitted trouser and fitted shirt the most effective is the rectangle shape (cluster 4) and the least is the circle shape (cluster 2) in the fabric consumption. Similarly, the fitted trousers utilize less fabric while the fitted shirts consume more fabric in all body shapes. These findings provide a better reference of fabric utilization and cost-effectiveness to the apparel manufacturers while producing garments for different categories of the body shape.

This companion paper supports the experimental replication of paper "Outfit Compatibility Prediction and Diagnosis with Multi-Layered Comparison Network", which is presented at ACM Multimedia 2019. We provide the software package for replicating the implementation of Multi-Layered Comparison Network (MCN), as well as the Polyvore-T dataset and baseline methods compared in the original paper. This paper contains the guides to reproduce the experiment results including outfit compatibility prediction, outfit diagnosis and automatic outfit revision.

The waterborne polyurethane (WPU) with different carboxylic acid group contents were prepared by a prepolymer method, adopting polycarbonate diol (PCDL) as soft segments and isophorone diisocyanate (IPDI) as hard segments. The different amounts of 2,2-dimethylolbutyric acid (DMPA) as hydrophilic chain extender were introduced into polyurethane molecular for studying the effect on microstructure and properties. The solid content, pH value and viscosity measurement were used to characterize the performance of WPU emulsion. The fourier transform infrared spectroscopy (FT-IR), X-ray diffraction (XRD), thermogravimetric (TG), differential scanning calorimetry (DSC), dynamic mechanical analysis (DMA), water contact angle tester and mechanical testing machine were utilized to measure the structure, crystallization performance, thermal stability, low temperature flexibility, wetting performance and mechanical properties of WPU films, respectively. The test value of impact, adhesive, flexibility and pencil hardness on tinplate of WPU coatings were obtained for observing film properties. The results indicated that the emulsification effect increase with the increased DMPA contents. The decomposition temperature of WPU films perform a slight decrease and the WPU films have excellence low temperature flexibility with the increased DMPA contents. The hydrophilic property of WPU films mainly are about 80°and the tensile strength value of 7 wt% WPU reaches 45 MPa and elongation at break at 420%.

Purpose The automatic body measurement is the key of tailoring, mass customization and fit/ease evaluation. The major challenges include finding the landmarks and extracting the sizes accurately. The purpose of this paper is to propose a new method of body measurement based on the loop structure. Design/methodology/approach The scanned human model is sliced equally to layers consist of various shapes of loops. The semantic feature analysis has been regarded as a problem of finding the points of interest (POI) and the loop of interest (LOI) according to the types of loop connections. Methods for determining the basic landmarks have been detailed. Findings The experimental results validate that the proposed methods can be used to locate the landmarks and to extract sizes on markless human scans robustly and efficiently. Originality/value With the method, the body measurement can be quickly performed with average errors around 0.5 cm. The results of segmentation, landmarking and body measurements also validate the robustness and efficiency of the proposed methods.

Due to the similarities between cashmere and wool, the automatic identification of these two animal fibers continues to be a huge challenge in textile society. In this paper, for the identification of micrographs of cashmere and wool, bag-of-words and spatial pyramid matching are used. Each fiber image was regarded as a collection of feature vectors in our logic. The vectors, extracted from the original dataset, were fed into a support vector machine for supervised classification. The codebook size and the resolution level were completely investigated. The experimental results indicated that the image segmentation delivered a positive contribution in enhancing the accuracy of classification. The overall performance of the model was robust under various blend ratios. It verifies that the bag-of-words with spatial pyramid match is an effective approach to the identification of cashmere and wool fibers.

Purpose The calibration is a key but cumbersome process for 3D body scanning using multiple depth cameras. The purpose of this paper is to simplify the calibration process by introducing a new method to calibrate the extrinsic parameters of multiple depth cameras simultaneously. Design/methodology/approach An improved method is introduced to enhance the accuracy based on the virtual checkerboards. Laplace coordinates are employed for a point-to-point adjustment to increase the accuracy of scanned data. A system with eight depth cameras is developed for full-body scanning, and the performance of this system is verified by actual results. Findings The agreement of measurements between scanned human bodies and the real subjects demonstrates the accuracy of the proposed method. The entire calibration process is automatic. Originality/value A complete algorithm for a full human body scanning system is introduced in this paper. This is the first publically study on the refinement and the point-by-point adjustment based on the virtual checkerboards toward the scanning accuracy enhancement.

In apparel manufacturing, more than 50% of the total cost is consumed by the fabric in comparison to the rest of the materials. The efficient use of fabric may result in the reduction of considerable expenditure and efforts. Therefore, the purpose of this study is to propose an image projected virtual marker (IPVM) onto the surface of fabric layers/plies to improve fabric utilization and visual quality control. 20 garment production orders are scheduled for experimental work to investigate the utilization of fabrics with imperfections. The statistical analysis indicates a 3.5%–4% improvement in the fabric utilization, a 22% improvement in throughput time of visual inspection, and a 25% reduction of labor intensity during visual inspection in the cutting room. The result implies that the proposed method is an efficient approach to improve fabric utilization and cost reduction.

In this paper, a new method was proposed to establish the relationship between three-dimensional (3D) foot shapes and their two-dimensional (2D) foot silhouettes, through which a complete 3D foot shape can be predicted by simply inputting its two 2D silhouettes. 3D foot scans of 80 participants were randomly selected as the training set, and those of another 20 participants were used as the testing set. Elliptical Fourier analysis (EFA) and principle component analysis (PCA) were adopted to parameterize the 3D foot shapes. A linear regressive model was then developed to predict the 3D foot shape with the foot silhouettes. Experiment results indicated individual 3D foot shape can be predicted with a mean error between 1.21 and 1.27 mm, which can provide enough accuracy for the fit evaluation of footwear.

3D garment model plays an important role in the fashion industry. However, not much work focus on extracting high-quality clothes from scanned data. The texture is limited by photography methods in 3D scanning. This paper proposes a novel framework of reconstructing high-quality 3D garment models with synthesized texture. Firstly, a pipeline of 3D garment processing is proposed to obtain a better 3D model based on KinectFusion. Then, DeepTextures is used to synthesize a new texture. To our best knowledge, this is the first paper combining 3D garment reconstruction and texture synthesis. Experimental results show that our method can conveniently obtain 3D garment models and realistic textures.

In this paper, 3D fabric drape was reconstructed by using video recorded from a smartphone. Elliptical Fourier Analysis (EFA) and Principle Component Analysis (PCA) were used to parameterize the 3D drape to reveal shape parameters. A cluster analysis of various 3D drapes was implemented to verify the proposed method. Experiment results demonstrated that the 3D drape can be reconstructed and parameterized with a mean error of 0.52 mm when the harmonic number of EFA equals to 25. The cluster result indicated that the new features detected by our method were useful to classify different drapes, which provided a novel idea for 3D drape analysis.

Image-based fabric retrieval technique can help to develop new fabrics and manage products. Efficiently extracting features from fabric images is the key to enhance the practicality of this technology. In this paper, convolutional neural network is trained with a dataset of 19,894 different yarn-dyed fabric patterns. Center loss architecture is added to further improve the discriminative power of the network. By properly sampling from original images, the network model can efficiently extract discriminative features and achieve a retrieval accuracy of 99.89% on our test set. This performance maintains well when simpler deep architecture is used, but decreases quickly if the contents of fed fabric image are reduced.

Wool fiber and cashmere fiber are similar in physical and morphological characteristics. Thus, the identification of these two fibers has always been a challenging proposition. This study identifies five kinds of cashmere and wool fibers using a convolutional neural network model. To this end, image preprocessing was first performed. Then, following the VGGNet model, a convolutional neural network with 13 weight layers was established. A dataset with 50,000 fiber images was prepared for training and testing this newly established model. In the classification layer of the model, softmax regression was used to calculate the probability value of the input fiber image for each category, and the category with the highest probability value was selected as the prediction category of the fiber. In this experiment, the total identification accuracy of samples in the test set is close to 93%. Among these five fibers, Mongolian brown cashmere has the highest identification accuracy, reaching 99.7%. The identification accuracy of Chinese white cashmere is the lowest at 86.4%. Experimental results show that our model is an effective approach to the identification of multi-classification fiber.

Human body modeling is an important part of virtual try-on. In order to quickly reconstruct the three-dimensional(3D) human body based on the minimum input, we propose a new method for accurate reconstruction of the human body by inputting binary images from either single view or multiple views. We first encode the shape of the human body via Principal Component Analysis (PCA) to extract the low dimensional shape descriptor. Secondly, we design a novel Body Reconstruction Convolutional Neural Network (BRCNN) with two branches, which could capture deep correlated features from different views and merge them. Given the obtained statistical shape space of the human body, we jointly train the BRCNN to learn a global mapping from the input to the shape descriptor which can be then decoded to points cloud for the reconstruction of various body shapes under neutral poses. The experimental results show that compared with the existing human reconstruction technology, the accuracy has been improved by 1.07%, and the prediction results of the two views are better than those from the single view. Further investigation also reveals that the prediction results of the weight-sharing network are better than the network without weight-sharing.