Virtual Dress Swap Using Landmark Detection
Odar Zeynal, Saber Malekzadeh
TL;DR
This paper presents a method for virtual dress swapping using landmark detection to enhance online shopping experiences, leveraging deep learning for accurate landmark identification.
Contribution
It introduces a novel approach combining landmark detection with deep learning to enable virtual dress swapping in online fashion retail.
Findings
Effective landmark detection achieved with deep convolutional neural networks.
Facilitates realistic virtual dress swapping for online shoppers.
Uses DeepFashion dataset with 6,223 images for training and evaluation.
Abstract
Online shopping has gained popularity recently. This paper addresses one crucial problem of buying dress online, which has not been solved yet. This research tries to implement the idea of clothes swapping with the help of DeepFashion dataset where 6,223 images with eight landmarks each used. Deep Convolutional Neural Network has been built for Landmark detection.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsFace recognition and analysis · 3D Shape Modeling and Analysis · Generative Adversarial Networks and Image Synthesis