VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss

TL;DR

VITON-GAN is a novel generative adversarial network that produces high-quality virtual try-on images from clothing and person images, effectively handling occlusions through adversarial training.

Contribution

This paper introduces VITON-GAN, a new adversarial network that improves virtual try-on image quality, especially in occluded scenarios, advancing the state of virtual fitting technology.

Findings

Enhanced image quality with occlusion handling

Effective adversarial training improves realism

Applicable to diverse clothing and body poses

Abstract

Generating a virtual try-on image from in-shop clothing images and a model person's snapshot is a challenging task because the human body and clothes have high flexibility in their shapes. In this paper, we develop a Virtual Try-on Generative Adversarial Network (VITON-GAN), that generates virtual try-on images using images of in-shop clothing and a model person. This method enhances the quality of the generated image when occlusion is present in a model person's image (e.g., arms crossed in front of the clothes) by adding an adversarial mechanism in the training pipeline.