SizeFlags: Reducing Size and Fit Related Returns in Fashion E-Commerce

Nestler, Andrea; Karessli, Nour; Hajjar, Karl; Weffer, Rodrigo; Shirvany, Reza

doi:10.1145/3447548.3467160

Cited by 19 publications

(14 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the contemporary economic environment, the sustainability of the Malaysian apparel industry has become a pressing issue. A study by Nestler et al, [21] highlights that the apparel industry is expected to have a high rate of return of 30 to 40 percent, and illfitting garments have become the main reason for returns, which not only affects consumer satisfaction, but also exacerbates the problem of waste in the apparel industry. Guo and Istook [22] further state that consumers often need help finding garments that fit well, which has led to many ill-fitting garments in the market.…”

Section: Sustainability and Apparel Industry In Malaysiamentioning

confidence: 99%

Influence of Size and Fit on Malaysian Apparel Industry Sustainability: A Scoping Review

Wang,

Zakaria

2024

Sustainability

View full text Add to dashboard Cite

Mass production and global trade have fuelled apparel industry economic growth since the industrial revolution. Mass production and global trade have also contributed to sustainability issues, such as pollution and resource depletion. This scoping review explores how garment sizing and fit affect the sustainability of the Malaysian garment industry. The research objective was achieved using an in-depth analysis of the literature to identify the main sizing and fit issues and research gaps in the Malaysian apparel industry. Furthermore, the sustainability challenges resulting from sizing and fit issues were explored and the strategies to address these issues for apparel industry sustainability were proposed. Finally, the authors suggest that Malaysia should establish its own standard sizing system to contribute to the sustainable development of the local industry. This comprehensive analysis aims to provide an empirical basis and strategic guide for sustainable development by the Malaysian apparel industry.

show abstract

Section: Sustainability and Apparel Industry In Malaysiamentioning

confidence: 99%

Influence of Size and Fit on Malaysian Apparel Industry Sustainability: A Scoping Review

Wang,

Zakaria

2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…They used the underlying structures in the feature space, such as the linear size relation for the same item and the manufacturer-specific size systems, to simplify the modelling. Nestler et al developed a Bayesian model based on size-specific returns to predict fit properties of individual fashion items [11]. A drawback of these statistical approaches is the cold start problem: there is no purchase history for newer items and, thus, no statistical information.…”

Section: Related Workmentioning

confidence: 99%

Three Step Volumetric Segmentation for Automated Shoe Fitting

Leipert¹,

Herl²,

Stebani³

et al. 2023

eJNDT

View full text Add to dashboard Cite

This work presents a three-step segmentation process based on Convolutional Neural Networks. The task is to identify the different parts of shoes from Computed Tomography scans of boxed pairs of shoes. The first step of the three-step algorithm uses a scaled-down volume image to separate the shoe material from its surroundings. The second step segments the shoe's inside volume, i.e. the space enclosed by shoe material. The third and last step splits the segmented shoe material into individual components: shoe upper material, outer and insole. The complete process employs CNNs derived from three-dimensional UNets. Residual SE UNet, Dense UNet, and Bottleneck Residual UNet are evaluated for the three steps. The architectures are modified for large receptive fields. The networks are trained and tested for each step separately and conjointly on CT scans comprising various shoe types. The test results inspire hope for using the process for automated segmentation and extraction of meshes from large batches of CT scans. In particular, the first step using a Residual SE UNet achieves an F1-score of 88.2 % for shoes and 58.9 % for the packing material. The second step segments the inside volume with an F1-score of 81.0 %. The third step segments the shoe into its components and achieves an F1-score for insole of 79.5 %, outer sole of 88.7 % and upper material of 81.3 %.

show abstract

“…Other methods provide article based size advice (e.g. recommending one size smaller than the usual) leveraging orders and returns data [14,15] or article images and attributes [16]. Further enriching the image based approach of [16], [17] introduced a body-aware visual embedding that captures clothing's affinity focusing on different body shapes.…”

Section: Related Workmentioning

confidence: 99%

FitGAN: Fit- and Shape-Realistic Generative Adversarial Networks for Fashion

Pecenakova¹,

Karessli²,

Shirvany³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Amidst the rapid growth of fashion e-commerce, remote fitting of fashion articles remains a complex and challenging problem and a main driver of customers' frustration. Despite the recent advances in 3D virtual try-on solutions, such approaches still remain limited to a very narrow -if not only a handful -selection of articles, and often for only one size of those fashion items. Other state-of-the-art approaches that aim to support customers find what fits them online mostly require a high level of customer engagement and privacy-sensitive data (such as height, weight, age, gender, belly shape, etc.), or alternatively need images of customers' bodies in tight clothing. They also often lack the ability to produce fit and shape aware visual guidance at scale, coming up short by simply advising which size to order that would best match a customer's physical body attributes, without providing any information on how the garment may fit and look. Contributing towards taking a leap forward and surpassing the limitations of current approaches, we present FitGAN, a generative adversarial model that explicitly accounts for garments' entangled size and fit characteristics of online fashion at scale. Conditioned on the fit and shape of the articles, our model learns disentangled item representations and generates realistic images reflecting the true fit and shape properties of fashion articles. Through experiments on real world data at scale, we demonstrate how our approach is capable of synthesizing visually realistic and diverse fits of fashion items and explore its ability to control fit and shape of images for thousands of online garments.

show abstract

SizeFlags: Reducing Size and Fit Related Returns in Fashion E-Commerce

Cited by 19 publications

References 29 publications

Influence of Size and Fit on Malaysian Apparel Industry Sustainability: A Scoping Review

Influence of Size and Fit on Malaysian Apparel Industry Sustainability: A Scoping Review

Three Step Volumetric Segmentation for Automated Shoe Fitting

FitGAN: Fit- and Shape-Realistic Generative Adversarial Networks for Fashion

Contact Info

Product

Resources

About