Fashion Images Research Articles

French Japonistes and their Collections of Hinagata Bon Pattern Books

Abstract This article examines little-known French collections of hinagata bon (Japanese pattern books) kept at the Musée des arts décoratifs in Paris, whose origins can be traced back to the travels of the first japonistes to Japan in the middle of the nineteenth century. The reception of these books by the French artists, collectors, and writers, who identified, analyzed, exhibited, and then preserved them for artistic, encyclopedic, and historical purposes, reveals the fascination the patterns and the cut of Japanese clothing held for early japonistes. Hinagata bon were originally intended for the textile industry, but in France served primarily to inspire artists and designers of every kind. Moreover, the books were also appreciated for their aesthetic value, which enables us to assess the role of japonistes in the conservation of Japanese fashion images.

Toward Attribute-Controlled Fashion Image Captioning

Fashion image captioning is a critical task in the fashion industry that aims to automatically generate product descriptions for fashion items. However, existing fashion image captioning models predict a fixed caption for a particular fashion item once deployed, which does not cater to unique preferences. We explore a controllable way of fashion image captioning that allows the users to specify a few semantic attributes to guide the caption generation. Our approach utilizes semantic attributes as a control signal, giving users the ability to specify particular fashion attributes (e.g., stitch, knit, sleeve) and styles (e.g., cool, classic, fresh) that they want the model to incorporate when generating captions. By providing this level of customization, our approach creates more personalized and targeted captions that suit individual preferences. To evaluate the effectiveness of our proposed approach, we clean, filter, and assemble a new fashion image caption dataset called FACAD170K from the current FACAD dataset. This dataset facilitates learning and enables us to investigate the effectiveness of our approach. Our results demonstrate that our proposed approach outperforms existing fashion image captioning models as well as conventional captioning methods. Besides, we further validate the effectiveness of the proposed method on the MSCOCO and Flickr30K captioning datasets and achieve competitive performance.

FICE: Text-conditioned fashion-image editing with guided GAN inversion

Fashion-image editing is a challenging computer-vision task where the goal is to incorporate selected apparel into a given input image. Most existing techniques, known as Virtual Try-On methods, deal with this task by first selecting an example image of the desired apparel and then transferring the clothing onto the target person. Conversely, in this paper, we consider editing fashion images with text descriptions. Such an approach has several advantages over example-based virtual try-on techniques: (i) it does not require an image of the target fashion item, and (ii) it allows the expression of a wide variety of visual concepts through the use of natural language. Existing image-editing methods that work with language inputs are heavily constrained by their requirement for training sets with rich attribute annotations or they are only able to handle simple text descriptions. We address these constraints by proposing a novel text-conditioned editing model called FICE (Fashion Image CLIP Editing) that is capable of handling a wide variety of diverse text descriptions to guide the editing procedure. Specifically, with FICE, we extend the common GAN-inversion process by including semantic, pose-related, and image-level constraints when generating images. We leverage the capabilities of the CLIP model to enforce the text-provided semantics, due to its impressive image–text association capabilities. We furthermore propose a latent-code regularization technique that provides the means to better control the fidelity of the synthesized images. We validate the FICE through rigorous experiments on a combination of VITON images and Fashion-Gen text descriptions and in comparison with several state-of-the-art, text-conditioned, image-editing approaches. Experimental results demonstrate that the FICE generates very realistic fashion images and leads to better editing than existing, competing approaches. The source code is publicly available from: https://github.com/MartinPernus/FICE.

Exploring databases for training models in machine learning in the Fashion industry

Growing interest in applying machine learning (ML) to fashion highlights the importance of using labeled data to develop models, facilitating research replication, and automating the analysis of new data, such as fashion show images available online. Despite this need, few studies, especially in Brazil, methodologically explore the intersection between fashion and AM. This research aims to provide an overview of online databases for training ML models. A systematic review identified 26 articles that use these databases, such as Fashion-MNIST and DeepFashion2. Content analysis revealed that these databases, including Polyvore and Fashion Image Dataset, have diverse applications, highlighting the transformative potential of AM in fashion and encouraging innovations in design, production, and marketing in the fashion industry.

Diffusion of fashion trend information: a study on fashion image mining from various sources

The advancement in the internet and mobile technologies has substantially altered information diffusion in modern society, creating a diverse environment for generating and sharing various forms of information. Specifically, the emergence of new information sources, such as influencers and online communities, has significantly influenced the formation of consumer opinion. We highlight the changes that have occurred in the diffusion of fashion trend information. To do this, we conducted data mining, which involved three main steps: data preprocessing, specifically converting image data (including images from the 2022 F/W season runway collection, fashion influencer outfits, and best items from online fashion retailers) into textual data; data mining analysis (quantitative analysis); and data post-processing. As a result, we found that even items with low or no appearance on the runway held significance in the best item data or fashion influencer outfits. Specifically, the best items on online fashion retailers, reflecting popular fashion trends, had greater similarity to fashion influencer outfits. However, similarities in silhouette attributes were found among runway collections, fashion influencer outfits, and best items data. This study holds great significance because it focuses on fashion items genuinely consumed by the mainstream consumers rather than only focusing on the four major runway collections. Furthermore, these findings offer valuable insights for merchandising and trend forecasting, emphasizing the importance of selectively utilizing fashion trend information in the planning of fashion products.

BangleFIR: bridging the gap in fashion image retrieval with a novel dataset of bangles

BangleFIR: bridging the gap in fashion image retrieval with a novel dataset of bangles

HairStyle Editing via Parametric Controllable Strokes.

In this work, we propose a stroke-based hairstyle editing network, dubbed HairstyleNet, allowing users to conveniently change the hairstyles of an image in an interactive fashion. Different from previous works, we simplify the hairstyle editing process where users can manipulate local or entire hairstyles by adjusting the parameterized hair regions. Our HairstyleNet consists of two stages: a stroke parameterization stage and a stroke-to-hair generation stage. In the stroke parameterization stage, we first introduce parametric strokes to approximate the hair wisps, where the stroke shape is controlled by a quadratic Bézier curve and a thickness parameter. Since rendering strokes with thickness to an image is not differentiable, we opt to leverage a neural renderer to construct the mapping from stroke parameters to a stroke image. Thus, the stroke parameters can be directly estimated from hair regions in a differentiable way, enabling us to flexibly edit the hairstyles of input images. In the stroke-to-hair generation stage, we design a hairstyle refinement network that first encodes coarsely composed images of hair strokes, face, and background into latent representations and then generates high-fidelity face images with desirable new hairstyles from the latent codes. Extensive experiments demonstrate that our HairstyleNet achieves state-of-the-art performance and allows flexible hairstyle manipulation.

Enhanced content-based fashion recommendation system through deep ensemble classifier with transfer learning

With the rise of online shopping due to the COVID-19 pandemic, Recommender Systems have become increasingly important in providing personalized product recommendations. Recommender Systems face the challenge of efficiently extracting relevant items from vast data. Numerous methods using deep learning approaches have been developed to classify fashion images. However, those models are based on a single model that may or may not be reliable. We proposed a deep ensemble classifier that takes the probabilities obtained from five pre-trained models such as MobileNet, DenseNet, Xception, and the two varieties of VGG. The probabilities obtained from the five pre-trained models are then passed as inputs to a deep ensemble classifier for the prediction of the given item. Several similarity measures have been studied in this work and the cosine similarity metric is used to recommend the products for a classified product given by a deep ensemble classifier. The proposed method is trained and validated using benchmark datasets such as Fashion product images dataset and Shoe dataset, demonstrating superior accuracy compared to existing models. The results highlight the potential of leveraging transfer learning and deep ensemble techniques to enhance fashion recommendation systems. The proposed model achieves 96% accuracy compared to the existing models.

Dominant Color Detection For Online Fashion Retrievals

This paper introduces a novel approach aimed at efficiently extracting dominant colors from online fashion images. The method addresses challenges related to detecting overlapping objects and computationally expensive methods by combining K-means clustering and graph-cut techniques into a framework. This framework incorporates an adaptive weighting strategy to enhance color extraction accuracy. Additionally, it introduces a two-phase fashion apparel detection method called YOLOv4, which utilizes U-Net architecture for clothing segmentation to precisely separate clothing items from the background or other elements. Experimental results show that K-means with YOLOv4 outperforms K-means with the U-Net model. These findings suggest that the U-Net architecture and YOLOv4 models can be effective methods for complex image segmentation tasks in online fashion retrieval and image processing, particularly in the rapidly evolving e-commerce environment.

Изменение эстетических идеалов под воздействием феномена культа молодости 1920-х годов

Introduction. The principle of aesthetic transformation affects not only the functioning of fashion, but also a range of problems related to the worldview and world perception of a person, which are relevant for any time. Aesthetic problems have a deeper foundation than the change of images of vestimentary fashion, and lie in the sphere of social and cultural life of society. Theoretical analysis. At certain points in history, the aggravation of social and cultural aspects of public life causes a change in the spiritual values developed over the centuries, followed by a revision of aesthetic ideals. In the period of the 1920s, youth became the dominant age category in the society, and the cult of youth appeared. The theoretical basis of this phenomenon was provided by T. Parsons, K. Mannheim, Х. Ortega-y-Gasset, J. Huizinga and others, justifying it by the conflict of generations, the lack of continuity between them. Conclusions. An attempt has been made to take an integrated approach to the analysis of a number of aspects of a socio-cultural nature in a certain time period, which served as the starting point for the emergence of the cult of youth. The phenomenon led to the reassessment of aesthetic ideals. Fashion reacted sensitively to it, youth images inspired bold new directions and determined its development for decades to come.

Conversational Fashion Outfit Generator Powered by GenAI

The convergence of artificial intelligence and fashion has given rise to innovative solutions that cater to the ever-evolving needs and preferences of fashion enthusiasts. This report delves into the methodology behind the development of a "Conversational Fashion Outfit Generator powered by GenAI," an advanced application that leverages the capabilities of Generative Artificial Intelligence (GenAI) to create personalized fashion outfits through natural language interactions. The model outlines the essential elements of the methodology, including data collection, natural language understanding, computer vision integration, and deep learning algorithms. Data collection forms the bedrock, as access to a diverse dataset of fashion-related information is critical for training and fine-tuning AI models. Natural Language Understanding (NLU) is instrumental in comprehending user input and generating context-aware responses, ensuring meaningful and engaging conversations. Computer vision technology is integrated to analyze fashion images, recognizing clothing items, styles, and colors, thus aiding in outfit recommendations. Deep learning algorithms, particularly recurrent and transformer-based models, form the backbone of the system, generating personalized and contextually relevant fashion suggestions. This methodology not only underpins the "Conversational Fashion Outfit Generator" but also reflects the evolving landscape of AI in the fashion industry, where personalized, interactive experiences are becoming increasingly paramount in the realm of fashion and e-commerce.

패션 이미지 데이터를 활용한 딥러닝 기반의 의류속성 분류

Attributes such as material, color, and fit in fashion images are important factors for consumers to purchase clothing. However, the process of classifying clothing attributes requires a large amount of manpower and is inconsistent because it relies on the subjective judgment of human operators. To alleviate this problem, there is a need for research that utilizes artificial intelligence to classify clothing attributes in fashion images. Previous studies have mainly focused on classifying clothing attributes for either tops or bottoms, so there is a limitation that the attributes of both tops and bottoms cannot be identified simultaneously in the case of full-body fashion images. In this study, we propose a deep learning model that can distinguish between tops and bottoms in fashion images and classify the category of each item and the attributes of the clothing material. The deep learning models ResNet and EfficientNet were used in this study, and the dataset used for training was 1,002,718 fashion images and 125 labels including clothing categories and material properties. Based on the weighted F1-Score, ResNet is 0.800 and EfficientNet is 0.781, with ResNet showing better performance.

Social4Fashion: An intelligent expert system for forecasting fashion trends from social media contents

The fashion field is continually expanding and evolving, and social media play a significant role in shaping current fashion trends through the influence of online personalities, such as influencers. As a result, fashion designers often turn to social media to gain insights into the latest trends and draw inspiration, while in the past they used to physically visit fashion districts. To automate and speed up this process, an expert system is much needed; thus, Social4Fashion has been created, an end-to-end framework that leverages deep learning-based techniques in order to support creatives in their research and decision-making process, with the final goal of analyzing and predicting trends. This system employs several steps, starting with the automatic data collection from Instagram, using hashtags provided by domain experts. Next, retrieved images are filtered to remove non-fashion related pictures, leaving only those pertaining to the fashion area for further processing. Then, to obtain more specific information about the images, the handbags present (if any) are detected and classified, based on their type; finally, dominant colors of the handbags are retrieved through clustering on the images. All the data collected with this system are then stored and analyzed via user-friendly dashboards, created with the objective of highlighting relevant information, in order to perform analysis on current and future fashion trends. Results show the effectiveness of the proposed system, with an accuracy of 97% (95% confidence interval 0.95–1) for the fashion image classification and a mAP of 0.77 (95% confidence interval 0.73–0.82) for the handbag detection, which makes it suitable for fashion domain analysis. Also, as a result of this work, a novel fashion-related dataset has been made available to the research community. This system can greatly improve the way fashion trends are analyzed, and allow for more efficient and effective design processes in the future.

TexFit: Text-Driven Fashion Image Editing with Diffusion Models

Fashion image editing aims to edit an input image to obtain richer or distinct visual clothing matching effects. Existing global fashion image editing methods are difficult to achieve rich outfit combination effects while local fashion image editing is more in line with the needs of diverse and personalized outfit matching. The local editing techniques typically depend on text and auxiliary modalities (e.g., human poses, human keypoints, garment sketches, etc.) for image manipulation, where the auxiliary modalities essentially assist in locating the editing region. Since these auxiliary modalities usually involve additional efforts in practical application scenarios, text-driven fashion image editing shows high flexibility. In this paper, we propose TexFit, a Text-driven Fashion image Editing method using diffusion models, which performs the local image editing only with the easily accessible text. Our approach employs a text-based editing region location module to predict precise editing region in the fashion image. Then, we take the predicted region as the generation condition of diffusion models together with the text prompt to achieve precise local editing of fashion images while keeping the rest part intact. In addition, previous fashion datasets usually focus on global description, lacking local descriptive information that can guide the precise local editing. Therefore, we develop a new DFMM-Spotlight dataset by using region extraction and attribute combination strategies. It focuses locally on clothes and accessories, enabling local editing with text input. Experimental results on the DFMM-Spotlight dataset demonstrate the effectiveness of our model. Code and Datasets are available at https://texfit.github.io/.

FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval

The goal of composed fashion image retrieval is to locate a target image based on a reference image and modified text. Recent methods utilize symmetric encoders (e.g., CLIP) pre-trained on large-scale non-fashion datasets. However, the input for this task exhibits an asymmetric nature, where the reference image contains rich content while the modified text is often brief. Therefore, methods employing symmetric encoders encounter a severe phenomenon: retrieval results dominated by reference images, leading to the oversight of modified text. We propose a Fashion Enhance-and-Refine Network (FashionERN) centered around two aspects: enhancing the text encoder and refining visual semantics. We introduce a Triple-branch Modifier Enhancement model, which injects relevant information from the reference image and aligns the modified text modality with the target image modality. Furthermore, we propose a Dual-guided Vision Refinement model that retains critical visual information through text-guided refinement and self-guided refinement processes. The combination of these two models significantly mitigates the reference dominance phenomenon, ensuring accurate fulfillment of modifier requirements. Comprehensive experiments demonstrate our approach's state-of-the-art performance on four commonly used datasets.

SPIRIT: Style-guided Patch Interaction for Fashion Image Retrieval with Text Feedback

Fashion image retrieval with text feedback aims to find the target image according to the reference image and the modification from the user. This is a challenging task, as it requires not only the synergistic understanding of both visual and textual modalities but also the ability to model a wide variety of styles that fashion images contain. Hence, the crucial aspect of addressing this problem lies in exploiting the abundant semantic information inherent in fashion images and correlating it with the textual description of style. Recognizing that style is generally situated at the local level, we explicitly define style as the commonalities and differences between local areas of fashion images. Building upon this, we propose a Style-guided Patch InteRaction approach for fashion Image retrieval with Text feedback (SPIRIT), which focuses on the decisive influence of local details of fashion images on their style. Three corresponding networks are designed pertinently. The Patch-level Style Commonality network is introduced to fully leverage the semantic information among patches and compute their average as the style commonality. Subsequently, the Patch-level Style Difference network employs a graph reasoning network to model the patch-level difference and filter out insignificant patches. By considering the above two networks, mutual information about style is obtained from the interaction between patches. Finally, the Visual Textual Fusion network is utilized to integrate visual features with rich semantic information and textual features. Experimental results on four benchmark datasets demonstrate that our proposed SPIRIT achieves state-of-the-art performance. Source code is available at https://github.com/PKU-ICST-MIPL/SPIRIT_TOMM2024 .

Crystal plasticity modeling of deformation behavior of Al–Al2Cu eutectics based on high-fidelity representative microstructures

A comprehensive understanding of material deformation behavior holds importance in enhancing the properties of materials, which can be achieved through modeling the relationship between microstructure and deformation behavior by an appropriate crystal plasticity (CP) model. However, before simulations, obtaining a high-fidelity representative microstructure (RM) to simultaneously meet the efficiency and accuracy requirements of the CP model is still a challenge. Thus, taking the Al–Al2Cu eutectics as an example, we successfully obtained a high-fidelity RM with two-point statistics and some fashionable image processing techniques. Then a high-resolution RMCP model was developed and the deformation behavior of Al–Al2Cu eutectics at room temperatures was uncovered. Due to multiple activated slip systems on {111}<110> inducing obvious cross-slip behavior, severe and heterogenous plastic deformation occurs in α-Al. And dislocations originate from the microstructure defects. In θ-Al2Cu, all possible slip systems are not activated, resulting in no plastic deformation. The predictions of the RMCP model are verified to be reliable by comparing with the results of in-situ tensile tests. Our proposed RMCP method is not only applicable to the two-phase eutectic systems, but also suitable for various multiphase and polycrystalline systems.

패션 아이템의 조합성을 활용한 구성적 해체주의 연구

Previous studies, literature, and photographic data were analyzed and considered theoretically and case-by-case, respectively, to reveal what socio-cultural changes caused the compositional tendency to deconstructivism in the past 10 years in various fusion environments. As a result, the increase in constructive deconstructionism using the combination of fashion items reflects the change in the public's flat view following the digitization of images, and the pursuit of newness through drastic fusion has increased as the consumption cycle of fashion images and products accelerates. In constructive deconstructionism using the combination of these fashion items, three common characteristics were found, which appeared as a type of emphasis on abstract reduction of details, proportional beauty through combination, and surreality through composition. This phenomenon of change can be understood as a process of development in which deconstructionism combines with constructive characteristics as a positive and universal aesthetic as the destructive and negative characteristics of the past are dismantled again in a new environment in which the fusion between heterogeneous things is positively accepted.

A Survey on Fashion Image Retrieval

Fashion is the manner in which we introduce ourselves to the world and has become perhaps the biggest industry on the planet. In recent years, fashion-related research has received a lot of attention from computer vision researchers as a result of the growing demand by the fashion industry. Fashion image retrieval (FIR) is a difficult initiative and requires finding the right items from a huge collection of fashion items based on an image query. FIR has been applied successfully to clothing and footwear. Despite ongoing advances, FIR still suffers from limitations when applied to real-world visual endeavors. However, research on complex design items, for example, ornaments, has received less attention due to the complex nature of similarity and the unavailability of suitable datasets. This article presents a review of FIR and evaluation systems from different design datasets. The motivation behind this review is, to sum up the state-of-the-art procedures for retrieving fashion images for a given query image. In addition, we highlight promising directions for future research.

Multichannel meta-imagers for accelerating machine vision.

Rapid developments in machine vision technology have impacted a variety of applications, such as medical devices and autonomous driving systems. These achievements, however, typically necessitate digital neural networks with the downside of heavy computational requirements and consequent high energy consumption. As a result, real-time decision-making is hindered when computational resources are not readily accessible. Here we report a meta-imager designed to work together with a digital back end to offload computationally expensive convolution operations into high-speed, low-power optics. In this architecture, metasurfaces enable both angle and polarization multiplexing to create multiple information channels that perform positively and negatively valued convolution operations in a single shot. We use our meta-imager for object classification, achieving 98.6% accuracy in handwritten digits and 88.8% accuracy in fashion images. Owing to its compactness, high speed and low power consumption, our approach could find a wide range of applications in artificial intelligence and machine vision applications.