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

Shion Honda
11/12/2019
cs.CV

Official code: shionhonda/viton-gan (107 stars, MIT, PyTorch, last commit 2019-11-20).

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.

View on arXivView PDF

Code Implementations(1)

shionhonda/viton-ganOfficial100%
PyTorchMIT

Original implementation of the paper "VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss" by Shion Honda.

10729PythonFeb 2, 20196 years agoMIT
computer-graphicscomputer-visiondeep-learningpythonpytorch+1 more

Similar Papers

Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images

90% match2023

Try-On-Adapter: A Simple and Flexible Try-On Paradigm

90% match2024

Learning Garment DensePose for Robust Warping in Virtual Try-On

90% match2023

From Keypoints to Realism: A Realistic and Accurate Virtual Try-on Network from 2D Images

90% match2025

Virtual Try-On with Pose-Garment Keypoints Guided Inpainting

90% match2023

Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks

89% match1 repo1642025

Cite this paper

@article{honda2019vitongan,
  title  = {VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss},
  author = {Shion Honda},
  year   = {2019},
  eprint = {1911.07926},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1911.07926}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1911.07926.svg)](https://codeofpaper.com/paper/1911.07926)

Discussion