FashionFit: Analysis of Mapping 3D Pose and Neural Body Fit for Custom Virtual Try-On

Abstract

Visual compatibility and virtual feel are critical metrics for fashion analysis yet are missing in existing fashion designs and platforms. An explicit model is much needed for implanting visual compatibility through fashion image inpainting and virtual try-on. With rapid advancements in the Computer Vision realm, the increase in creating customer experience which leads to the great potential of interest to retailers and customers. The public datasets available are very much fit for generating outfits from Generative Adversarial Networks (GANs) but the custom outfits of the users themselves lead to low accuracy levels. This work is the first step in analyzing and experimenting with the fit of custom outfits and visualizing it to the users on them which creates the great customer experience. The work analyses the need for providing visualization of custom outfits on users in the large corpora of AI in Fashion. The authors propose a novel architecture which facilitates the combining outfits provided by the retailers and visualize it on the users themselves using Neural Body Fit. This work creates a benchmark in disentangling the custom generation of cloth outfits using GANs and virtually trying it on the users to ensure a virtual-photorealistic appearance and results to create a great customer experience by using AI. Extensive experiments show the high accuracy levels on custom outfits generated by GANs but not in customized levels. This experiment creates new state-of-art results by plotting users pose for calculating the lengths of each body-part segment (hand, leg, and so forth), segmentation + NBF for accurate fitting of the cloth outfit. This paper is different from all other competitors in terms of approach for the virtual try-on for creating a new customer experience. INDEX TERMS Neural body fit, generative adversarial networks (GANs), pose, customer experience, segmentation.

LARNet: Real-Time Detection of Facial Micro Expression Using Lossless Attention Residual Network

“…F1 score was plotted to evaluate the performance metrics on the training patch and testing patch [ 45 , 46 ]. Each feature and its weight are updated at each epoch.…”

“…Therefore, the evaluation of the network is done with the F1 score, which is calculated using precision and recall as dependent parameters. F1 score is given by the parameters true positives ( ) as correct predictions, false negatives ( ) as false non-detections, and false positives ( ) as false correct predictions [ 45 , 46 ]. The mathematical computations for the above-mentioned parameters are as follows: …”

“…The video captured with 200 fps at 1080p resolution, that is, 1920 × 1080 pixel resolution was converted into 200 frames captured per second. F1 score was plotted to evaluate the performance metrics on the training patch and testing patch [45,46]. Each feature and its weight are updated at each epoch.…”

From Street Photos to Fashion Trends: Leveraging User-Provided Noisy Labels for Fashion Understanding

“…However, existing street fashion datasets mainly cover American and European street photos, which are not suitable for our goal. To address this issue, we have created RichWear, 3 a new dataset that focuses on the street fashion styles in Japan and other Asian areas.…”

“…As interest has increased in the possible relationships between artificial intelligence (AI) and fashion, more and more approaches are being proposed for fashion recognition and understanding. Meanwhile, fashion retailers are using AI technologies in inventory management, clothing recommendation, and virtual clothes fitting to improve their decisionmaking and competitive advantages [1]- [3].…”