Publications

In this paper, we present an interactive Virtual Reality (VR) application for fashion designers that aims to offer an immersive environment for accurately visualizing and testing garments in the design process. The VR environment simulates a designer’s fitting room, offering close up inspection of an avatar wearing a garment in a plethora of movements. This, in turn, offers to the designer a better perspective of how the final product will look, fit and behave. In implementing the proposed application, we first review the option in game engines and libraries to support a realistic avatar garment simulation, and propose a methodology for transforming the production-designed garments into a format that can be used in game engine cloth simulations.

In this paper, we present Snapwear, a Snapchat AR filter for visualizing real-world clothing in a magic mirror-alike experience with the use of a smartphone. Our objective is to document the steps needed to transform a garment designed for production to be ready-for-use in an AR environment. In this direction, we analyse the generation pipeline of an average avatar, the garment export from the fashion design software, its skinning and rigging to the average avatar and the simulation options offered by Snapchat. Finally, we discuss the AR experience creation process ranging from technical challenges such us body tracking and dealing with occlusions, to enabling the user interaction with the filter.

Fine-grained information extraction from fashion imagery is a challenging task due to the inherent diversity and complexity of fashion categories and attributes. Additionally, fashion imagery often depict multiple items while fashion items tend to follow hierarchical relations among various object types, categories and attributes. In this study, we address both issues with a 2-step hierarchical deep learning pipeline consisting of (1) a low granularity object type detection module (upper-body, lower-body, full-body, footwear) and (2) two classification modules for garment categories and attributes based on the outcome of the first step. For the category and attribute-level classification stages we examine a hierarchical label sharing (HLS) technique in two settings: (1) single-task learning (STL w/ HLS) and (2) multi-task learning with RNN and visual attention (MTL w/ RNN+VA). Our approach enables progressively focusing on appropriately detailed features for automatically learning the hierarchical relations of fashion and enabling predictions on images with complete outfits.
Empirically, STL w/ HLS reached 93.99% top-3 accuracy while MTL w/ RNN+VA reached 97.57% top-5 accuracy for category classification on the DeepFashion benchmark, surpassing the current state-of-the-art without requiring landmark or mask annotations nor specialised domain expertise.

Being able to forecast the popularity of new garment designs is very important in an industry as fast paced as fashion, both in terms of profitability and reducing the problem of unsold inventory. Here, we attempt to address this task in order to provide informative forecasts to fashion designers within a virtual reality designer application that will allow them to fine tune their creations based on current consumer preferences within an interactive and immersive environment. To achieve this we have to deal with the following central challenges: (1) the proposed method should not hinder the creative process and thus it has to rely only on the garment’s visual characteristics, (2) the new garment lacks historical data from which to extrapolate their future popularity and (3) fashion trends in general are highly dynamical. To this end, we develop a computer vision pipeline fine tuned on fashion imagery in order to extract relevant visual features along with the category and attributes of the garment. We propose a hierarchical label sharing (HLS) pipeline for automatically capturing hierarchical relations among fashion categories and attributes. Moreover, we propose MuQAR, a Multimodal Quasi-AutoRegressive neural network that forecasts the popularity of new garments by combining their visual features and categorical features while an autoregressive neural network is modelling the popularity time series of the garment’s category and attributes. Both the proposed HLS and MuQAR prove capable of surpassing the current state-of-the-art in key benchmark datasets, DeepFashion for image classification and VISUELLE for new garment sales forecasting.

In order to consider fashion outfits as aesthetically pleasing, the garments that constitute them need to be compatible in terms of visual aspects, such as style, category and color. With the advent and omnipresence of computer vision deep learning models, increased interest has also emerged for the task of visual compatibility detection with the aim to develop quality fashion outfit recommendation systems. Previous works have defined visual compatibility as a binary classification task with items in a garment being considered as fully compatible or fully incompatible. However, this is not applicable to Outfit Maker applications where users create their own outfits and need to know which specific items may be incompatible with the rest of the outfit. To address this, we propose the Visual InCompatibility TransfORmer (VICTOR) that is optimized for two tasks: 1) overall compatibility as regression and 2) the detection of mismatching items. Unlike previous works that either rely on feature extraction from ImageNet-pretrained models or by end-to-end fine tuning, we utilize fashion-specific contrastive language-image pre-training for fine tuning computer vision neural networks on fashion imagery. Moreover, we build upon the Polyvore outfit benchmark to generate partially mismatching outfits, creating a new dataset termed Polyvore-MISFITs, that is used to train VICTOR. A series of ablation and comparative analyses show that the proposed architecture can compete and even surpass the current state-of-the-art on Polyvore datasets while reducing the instance-wise floating operations by 88%, striking a balance between high performance and efficiency.

Estimating the preferences of consumers is of utmost importance for the fashion industry as appropriately leveraging this information can be beneficial in terms of profit. Trend detection in fashion is a challenging task due to the fast pace of change in the fashion industry. Moreover, forecasting the visual popularity of new garment designs is even more demanding due to lack of historical data. To this end, we propose MuQAR, a Multimodal Quasi-AutoRegressive deep learning architecture that combines two modules: (1) a multimodal multilayer perceptron processing categorical, visual and textual
features of the product and (2) a quasi-autoregressive neural network modelling the “target” time series of the product’s attributes along with the “exogenous” time series of all other attributes. We utilize computer vision, image classification and image captioning, for automatically extracting visual features and textual descriptions from the images of new products. Product design in fashion is initially expressed visually and these features represent the products’ unique characteristics without interfering with the creative process of its designers by requiring additional inputs (e.g manually written texts). We employ the product’s target attributes time series as a proxy of temporal popularity patterns, mitigating the lack of historical data, while exogenous time series help capture trends among interrelated attributes. We perform an extensive ablation analysis on two large scale image fashion datasets, Mallzee-P and SHIFT15m to assess the adequacy of MuQAR and also use the Amazon Reviews: Home and Kitchen dataset to assess generalisation to other domains. A comparative study on the VISUELLE dataset, shows that MuQAR is capable of competing and surpassing the domain’s current state of the art by 4.65% and 4.8% in terms of WAPE and MAE respectively.