VTON-IT: Virtual Try-On using Image Translation

TL;DR

This paper introduces VTON-IT, a GAN-based image translation method for virtual clothing try-on that produces high-resolution, realistic images by segmenting body parts and overlaying clothing, handling pose and occlusion variations.

Contribution

The paper presents a novel GAN-based image translation architecture that improves realism and alignment in virtual try-on applications using semantic segmentation.

Findings

Produces high-resolution, realistic images with detailed textures

Handles pose variations and occlusions effectively

Outperforms state-of-the-art GAN-based virtual try-on methods

Abstract

Virtual Try-On (trying clothes virtually) is a promising application of the Generative Adversarial Network (GAN). However, it is an arduous task to transfer the desired clothing item onto the corresponding regions of a human body because of varying body size, pose, and occlusions like hair and overlapped clothes. In this paper, we try to produce photo-realistic translated images through semantic segmentation and a generative adversarial architecture-based image translation network. We present a novel image-based Virtual Try-On application VTON-IT that takes an RGB image, segments desired body part, and overlays target cloth over the segmented body region. Most state-of-the-art GAN-based Virtual Try-On applications produce unaligned pixelated synthesis images on real-life test images. However, our approach generates high-resolution natural images with detailed textures on such variant images.