Clothing Regions Research Articles

Clothing-invariant contrastive learning for unsupervised person re-identification

Clothing change person re-identification (CC-ReID) aims to match images of the same person wearing different clothes across diverse scenes. Leveraging biological features or clothing labels, existing CC-ReID methods have demonstrated promising performance. However, current research primarily focuses on supervised CC-ReID methods, which require a substantial number of manually annotated labels. To tackle this challenge, we propose a novel clothing-invariant contrastive learning (CICL) framework for unsupervised CC-ReID task. Firstly, to obtain clothing change positive pairs at a low computational cost, we propose a random clothing augmentation (RCA) method. RCA initially partitions clothing regions based on parsing images, then applies random augmentation to different clothing regions, ultimately generating clothing change positive pairs to facilitate clothing-invariant learning. Secondly, to generate pseudo-labels strongly correlated with identity in an unsupervised manner, we design semantic fusion clustering (SFC), which enhances identity-related information through semantic fusion. Additionally, we develop a semantic alignment contrastive loss (SAC loss) to encourages the model to learn features strongly correlated with identity and enhances the model’s robustness to clothing changes. Unlike existing optimization methods that forcibly bring closer clusters with different pseudo-labels, SAC loss aligns the clustering results of real image features with those generated by SFC, forming a mutually reinforcing scheme with SFC. Experimental results on multiple CC-ReID datasets demonstrate that the proposed CICL not only outperforms existing unsupervised methods but can even achieves competitive performance with supervised CC-ReID methods. Code is made available at https://github.com/zqpang/CICL.

CS-VITON: a realistic virtual try-on network based on clothing region alignment and SPM

CS-VITON: a realistic virtual try-on network based on clothing region alignment and SPM

PAINT: Photo-realistic Fashion Design Synthesis

In this article, we investigate a new problem of generating a variety of multi-view fashion designs conditioned on a human pose and texture examples of arbitrary sizes, which can replace the repetitive and low-level design work for fashion designers. To solve this challenging multi-modal image translation problem, we propose a novel Photo-reAlistic fashIon desigN synThesis (PAINT) framework, which decomposes the framework into three manageable stages. In the first stage, we employ a Layout Generative Network (LGN) to transform an input human pose into a series of person semantic layouts. In the second stage, we propose a Texture Synthesis Network (TSN) to synthesize textures on all transformed semantic layouts. Specifically, we design a novel attentive texture transfer mechanism for precisely expanding texture patches to the irregular clothing regions of the target fashion designs. In the third stage, we leverage an Appearance Flow Network (AFN) to generate the fashion design images of other viewpoints from a single-view observation by learning 2D multi-scale appearance flow fields. Experimental results demonstrate that our method is capable of generating diverse photo-realistic multi-view fashion design images with fine-grained appearance details conditioned on the provided multiple inputs. The source code and trained models are available at https://github.com/gxl-groups/PAINT .

Wrinkles Realistic Clothing Reconstruction by Combining Implicit and Explicit Method

We propose a novel method to achieve robust and wrinkle-realistic clothing reconstruction from a single RGB image. Our approach successfully exploits both advantages of implicit function methods and explicit clothing generative models. The former allows to capture high-frequency wrinkle details and clothing appearance from a single image, and the latter provides reasonable clothing shape prior and structured topology. To utilize the implicit function method to obtain implicit clothing, the key is that we need to automatically segment the clothing region from the reconstructed results and solve its depth ambiguity problem. Therefore, we design a pixel-aligned segmentation method to achieve automatic and complete clothing segmentation. It relies on a lightweight clothing mask network and a simple but effective segmentation strategy. To deal with the depth ambiguity problem, a depth correction function is introduced to significantly remove the uncertainty in the depth direction and recover the correct clothing shape. Further, we utilize explicit clothing generative models to provide reasonable shapes and topologies. It first infers an initial explicit clothing template based on generative models. Then, the implicit clothing is fitted by this explicit template to capture high-frequency deformation, resulting in wrinkle-realistic and structured clothing results. Extensive experiments have proved the validity of our approach with the visual effect and geometry accuracy both reaching the state-of-the-art level in clothing reconstruction from a single image.

Clothing Style Recognition and Design by Using Feature Representation and Collaboration Learning

In order to recognize the clothing style, this paper establishes a standard clothing style library. The images of clothing style are provided and annotated by fashion design experts. The clothing style image is represented as a set of line segments that is obtained by detecting the lines and corners consisting of the edge feature points in the image. Then, the authors extract the features of the line segment set and use the extracted features to establish clothing style matching rules to make the system automatically produce the matching and recognizing criteria for the clothing style images. When inputting an image of a person wearing clothes, they first find the position of the person through skin color detection and then locate the clothing. The clothing region is segmented by seed growth algorithm. The features of the segmentation are compared with clothing style matching rules to determine the style. The experimental results show that the recognition rate of clothing style can reach more than 92% for the standard clothing images and more than 91% for real clothing images.

An Episodic Learning Network for Text Detection on Human Bodies in Sports Images

Due to the proliferation of sports-related multimedia content on the WWW, effective visual search and retrieval present interesting research challenges. These are caused by poor image quality, a wide range of possible camera points of view, pose variations on the part of athletes engaged in playing a sport, deformations of text appearing on sports person’s clothing and uniforms in motion, occlusions caused by other objects, etc. To address these challenges, this paper presents a new method for detecting text on human bodies in sports images. Unlike most existing methods, which attempt to exploit locations of a player’s torso, face, and skin, we propose an end-to-end episodic learning approach that employs inductive learning criteria for detecting clothing regions in an image, which are, in turn, then used for text detection. Our method integrates a Residual Network (ResNet) and Pyramidal Pooling Module (PPM) for generating a spatial attention map. The Progressive Scalable Expansion Algorithm (PSE) is adapted for text detection from these regions. Experimental results on our own dataset as well as several benchmarks (like RBNR and MMM which contain images of runners in marathons, and Re-ID which is a person re-identification dataset) demonstrate that the proposed method outperforms existing methods in terms of precision and F1-score. We also present results for sports images chosen from natural scene text detection datasets such as CTW1500 and MS-COCO to show the proposed method is effective and reliable across a range of inputs.

SPG-VTON: Semantic Prediction Guidance for Multi-Pose Virtual Try-on

Image-based virtual try-on is challenging in fitting a target in-shop clothes onto a reference person under diverse human poses. Previous works focus on preserving clothing details ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.,</i> texture, logos, patterns) when transferring desired clothes onto a target person under a fixed pose. However, the performances of existing methods significantly dropped when extending existing methods to multi-pose virtual try-on. In this paper, we propose an end-to-end Semantic Prediction Guidance multi-pose Virtual Try-On Network (SPG-VTON), which can fit the desired clothing into a reference person under arbitrary poses. Specifically, SPG-VTON is composed of three sub-modules. First, a Semantic Prediction Module (SPM) generates the desired semantic map. The predicted semantic map provides more abundant guidance to locate the desired clothing region and produce a coarse try-on image. Second, a Clothes Warping Module (CWM) warps in-shop clothes to the desired shape according to the predicted semantic map and the desired pose. Specifically, we introduce a conductible cycle consistency loss to alleviate the misalignment in the clothing warping process. Third, a Try-on Synthesis Module (TSM) combines the coarse result and the warped clothes to generate the final virtual try-on image, preserving details of the desired clothes and under the desired pose. In addition, we introduce a face identity loss to refine the facial appearance and maintain the identity of the final virtual try-on result at the same time. We evaluate the proposed method on the most massive multi-pose dataset (MPV) and the DeepFashion dataset. The qualitative and quantitative experiments show that SPG-VTON is superior to the state-of-the-art methods and is robust to data noise, including background and accessory changes, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , hats and handbags, showing good scalability to the real-world scenario.

Multiple Pose Virtual Try-On Based on 3D Clothing Reconstruction

Recently, image-based virtual try-on (VTON) systems using deep generative models have drawn significant research attention. However, the 2D clothing shape transform methods in the earlier works show serious limitations in 3D clothing deformation required in multiple-pose VTON scenarios. In this paper, we develop a 3D-MPVTON system of two pipelines and show that a 3D clothing model reconstruction approach provides much better results for the multi-pose VTON scenario. First, the 3D clothing model reconstruction pipeline is based on CloTH-VTON+. The try-on clothing is matched to the target clothing regions in the simply-shaped reference human model and its 3D model is reconstructed using the associated 3D human body model. For natural clothing rendering from an arbitrary view, accurate texture mapping is crucial. We have developed a highly accurate texture matching method. The try-on pipeline first generates target segmentation from the target pose for conditional information for the following stage’s network models. Correct target segmentation was one of the main performance bottlenecks in previous VTON studies. Our proposed equalized entropy loss for the target segmentation generation network greatly reduces the segmentation label imbalance, and results in high-quality segmentation and reduced training time. The rigged reconstructed 3D clothing model can be easily deformed into the target pose and the human body shape while retaining the textures of the clothes. The remaining parts, i.e., the non-target clothing regions of the human in the target pose are generated through a deep generative human pose transfer model. Finally, the generated clothing and the remaining parts are combined using conditional generative networks to in-paint the dis-occluded areas and blend them together. Our proposed hybrid pipeline outperforms the previous 2D-based approaches by substantial margins in both objective evaluation and subjective user study, especially in the cases of the large pose and viewpoint changes.

CloTH-VTON+: Clothing Three-Dimensional Reconstruction for Hybrid Image-Based Virtual Try-ON

Image-based virtual try-on (VTON) systems based on deep learning have attracted research and commercial interests. Although they show their strengths in blending the person and try-on clothing image and synthesizing the dis-occluded regions, their results for complex-posed persons are often unsatisfactory due to the limitations in their geometry deformation and texture-preserving capacity. To address these challenges, we propose CloTH-VTON+ for seamlessly integrating the image-based deep learning methods and the strength of the 3D model in shape deformation. Specifically, a fully automatic pipeline is developed for 3D clothing model reconstruction and deformation using a reference human model: first, the try-on clothing is matched to the target clothing regions in the simple shaped reference human model, and then the 3D clothing model is reconstructed. The reconstructed 3D clothing model can generate a very natural pose and shape transfer, retaining the textures of clothes. A clothing refinement network further refines the alignment, eliminating the misalignment due to the errors in human pose estimation and 3D deformation. The deformed clothing images are combined utilizing conditional generative networks to in-paint the dis-occluded areas and blend them all. Experiments on an existing benchmark dataset demonstrate that CloTH-VTON+ generates higher quality results in comparison to the state-of-the-art VTON systems and CloTH-VTON. CloTH-VTON+ can be incorporated into extended applications such as multi-pose guided and Video VTON.

A study of a clothing image segmentation method in complex conditions using a features fusion model

According to a priori knowledge in complex conditions, this paper proposes an unsupervised image segmentation algorithm to be used for clothing images that combines colour and texture features. First, block truncation encoding is used to divide the traditional three-dimensional colour space into a six-dimensional colour space so that more fine colour features can be obtained. Then, a texture feature based on the improved local binary pattern (LBP) algorithm is designed and used to describe the clothing image with the colour features. After that, according to the statistical appearance law of the object region and background information in the clothing image, a bisection method is proposed for the segmentation operation. Since the image is divided into several subimage blocks, bisection image segmentation will be accomplished more efficiently. The experimental results show that the proposed algorithm can quickly and effectively extract effective clothing regions from complex circumstances without any artificial parameters. The proposed clothing image segmentation method will play an important role in computer vision, machine learning applications, pattern recognition and intelligent systems.

How to Wear Beautifully? Clothing Pair Recommendation

In this paper, we present a practical system to automatically suggest the most pairing clothing items, given the reference clothing (upper-body or low-body). This has been a challenge, due to clothes having a variety of categories. Clothing is one of the most informative cues for human appearance. In our daily life, people need to wear properly and beautifully to show their confidence, politeness and social status in various occasions. However, it is not easy to decide what to wear and how to coordinate their own clothes. To address this problem, we propose a recommendation approach that includes clothing region detection, clothing pair recommendation and distance fusion. Clothing region detection based on Faster R-CNN is used to detect clothing region. Clothing pair recommendation consists of a quadruple network architecture, where one dual network of the architecture adopts Siamese convolution neural network architecture. Training examples are pairs of upper-body and low-body clothing items that are either compatible or incompatible. The other dual network is used to learn clothing style features of the input image. This framework is designed to learn a feature transformation from the images of clothing items into two latent spaces, which we call them compatible space and style space respectively. After training the two dual networks, we use a distance fusion method to fuse the features extracted from the compatible and style dual networks. To acquire an optimized model and verify our proposed method, we expand an existing large clothing dataset WoG (Weather-to-Garment), and the resulted dataset is called “How to Wear Beautifully” (H2WB). Experiments on the H2WB dataset demonstrate that our approach is effective with clothing region detection and clothing pair recommendation as well as distance fusion.

Clothing Cosegmentation for Shopping Images With Cluttered Background

In this paper, we address an important and practical problem of clothing cosegmentation (CCS): given multiple fashion model photos with natural backgrounds on e-commerce websites, to automatically and simultaneously segment all images and extract the clothing regions. However, cluttered backgrounds, variations in colors and styles, and inconsistent human poses all make it a challenging task. In this paper, a novel CCS algorithm is proposed to improve the accuracy of clothing extraction by exploiting the properties of multiple clothing images with the same apparel. First, the co-salient objects are computed by detecting the upper bodies of fashion models and transferring their locations within multiple images. Based on the coarse clothing regions determined by the upper body localization and co-salient object detection, the foreground (clothing) and background Gaussian mixture models are estimated, respectively. Finally, the clothing region in each image is extracted through energy minimization based on graph cuts iteratively. The proposed cosegmentation algorithm is mainly designed for multiple clothing images. As a byproduct, it can also be applied to single image segmentation without any modification. The experiments demonstrate that the proposed approach outperforms the state-of-the-art cosegmentation methods as well as traditional single image segmentation solution for shopping images.

Distribution and Type of Crash Damage to Motorcyclists’ Clothing: Validation of the Zone Approach in the European Standard for Motorcycle Protective Clothing, EN13595

Objective: Though the use of protective clothing reduces the risk of injury for motorcycle riders, not all protective clothing performs the same in crashes. A European Standard for motorcycle protective clothing (EN13595) was released in 2002 that specifies 4 zones in motorcycle clothing with different levels of protective qualities and 4 different test methods for assessing damage resistance. This project examined damage location and type in clothing worn by riders following a crash to establish the distribution of impact points and validate the zones described in EN13595. Method: Data from 117 crashed motorcycle riders collected during crash investigation were examined. These data included medical data and clothing inspections and contained 576 cases of clothing damage. To ensure that the impact point distribution included all possible contact locations, an additional 433 distinct injury locations were examined where injury had occurred but clothing was either undamaged or not present at that location. Descriptive techniques were used in the analysis. Results: The majority of damage occurred in areas covering the extremities or pelvic girdle (93%), with most occurring on the wrists and hands (18%) and ankles and feet (18%). Clothing regions covering the shoulder (10%), forearm (10%), elbow (9%), thigh (7%), lower leg (6%), and pelvic–hip region (5%) were also frequently damaged. Other body regions contributed only 8 percent of damage seen. Analysis of distinct injury locations demonstrated a similar distribution of impact. The most common types of clothing damage were abrasion, accounting for 69 percent, and torn material, which accounted for 26 percent of all damage. Further, the majority of material abrasion and tearing occurred in regions corresponding to zone 1, followed by zones 2, 3, and then 4. There were very few instances (3%) of burst and cut damage. Conclusions: The results are in agreement with the general concept of the zones used in the EU Standard. However, these results indicate that minor adjustments may be warranted. In particular, the number of impacts to the forearm and lower leg suggest that these regions might be better protected by considering the whole regions as zone 1or 2 rather than the multiple regions as currently indicated in the EU Standard. However, the subjective nature of determining the zone in which damage (and/or injury) occurred limits these findings and any others that attempt to validate the zone principles using real-world data. Further validation requires consideration of the severity of impact at different zones.

Comparison of regional efficacy and complications in the treatment of aberrant Mongolian spots with the Q-switched ruby laser

Background and objective: Aberrant Mongolian spots (AMS) distal from the lumbosacral region are said to be more apt to persist than the typical sacral AMS, so the Q-switched ruby laser (QSRL) has been the treatment of choice for AMS. However, so far as we could determine, there is no statistical analysis of the treatment of AMS. This paper shows statistical comparisons of the efficacy and complications in the treatment of AMS with QSRL. Methods: Fifty-three patients (16 males and 37 females) with 57 AMS regions were treated with the QSRL from March 1999 to April 2007, and we divided the diseased areas into exposed regions that could not be concealed by clothing and non-exposed regions that could be concealed by clothing, and performed a statistical analysis. Results: The results indicated that QSRL treatment of AMS in the exposed regions showed significantly improved coloration and caused less pigmentation when compared with the non-exposed regions. Conclusion: We concluded that QSRL treatment of AMS in the exposed regions is more effective than that of AMS in the non-exposed regions.

The Fashion Industry in Galicia: Understanding the 'Zara' Phenomenon

Galicia is traditionally one of the weaker regional economies in Spain. However it is home to one of the most successful global marketing phenomena of the age. Zara, the mid-market fashion arm of the Galician INDITEX Group, is amongst the 'culprits' that have been blamed for the demise from high street hegemony of such European retail notables as C&A, Littlewoods and Marks & Spencer. In this paper an analysis is provided of the mechanisms by which this peripheral region has succeeded in producing, from virtually nothing, a globally outstanding retail fashion industry in one of the world's most cutthroat competitive industries. It is shown that regional, national and supra-national factors have had important parts to play, but that the Galician approach is nevertheless unique, compared to that of other fashion clothing regions. Among the special features at play are high levels of tacit and codified knowledge exploitation, integrated design, production and retailing and advanced retail feedback technology that enables anticipation of customer preference.