vton
Datasets
All datasets matching “vton”VTON-Synthetic-Pairs
Dataset Card for Glance VTON Synthetic Dataset
Dataset Summary
The Glance VTON Synthetic Dataset is a large-scale, fully synthetic paired dataset designed for training and evaluating Virtual Try-On (VTON) models. It was created to overcome the scarcity, high acquisition cost, restrictive commercial licensing, and demographic/stylistic biases of existing real-world paired VTON datasets.
The dataset features carefully curated pairs consisting of an isolated garment image… See the full description on the dataset page: https://huggingface.co/datasets/glanceai/VTON-Synthetic-Pairs.Tstars-VTON
Tstars-Tryon 1.0
Commercial Applications
Our virtual try-on model, Tstars-Tryon 1.0, is now deployed on the Taobao App.
Simply scan the QR code below with the Taobao app to instantly try on your favorite looks.
We hope you enjoy a seamless and delightful shopping experience!
Tstars-VTON - MetaInfo
Introduction
Tstars-VTON is a comprehensive benchmark designed to evaluate whether a virtual try-on… See the full description on the dataset page: https://huggingface.co/datasets/TaobaoTmall-AlgorithmProducts/Tstars-VTON.VTON-Baselines
VTON-Baselines Dataset / VTON-Baselines 数据集
This dataset contains the baseline results of 2D virtual try-on methods evaluated on the test sets of VITON-HD and DressCode datasets.
本数据集包含了多个 2D 虚拟试穿方法在 VITON-HD 和 DressCode 两个公开数据集测试集上的基线结果。
Overview / 概述
This repository provides comprehensive baseline results from state-of-the-art virtual try-on methods, enabling fair comparison and benchmarking of different approaches in the virtual try-on domain.… See the full description on the dataset page: https://huggingface.co/datasets/zhengchong/VTON-Baselines.vtonqa
VTONQA: A Multi-Dimensional Quality Assessment Dataset for Virtual Try-On
📌 Overview
VTONQA is a benchmark dataset for evaluating the quality of virtual try-on (VTON) results.It provides multi-dimensional human annotations to assess realism, alignment, and perceptual quality of synthesized try-on images.
Compared with existing VTON datasets, VTONQA focuses on quality assessment rather than generation, enabling standardized evaluation across different methods.
🎯… See the full description on the dataset page: https://huggingface.co/datasets/weixiny0408/vtonqa.vton-temp-uploadsvtonqbench
VTON-QBench
Dataset Summary
VTON-QBench is a large-scale human-annotated benchmark for image quality assessment in image-based Virtual Try-On (VTON). It is designed to support reference-free, human-aligned evaluation of generated try-on images, where a ground-truth image of the same person wearing the target garment is typically unavailable.
The dataset contains 62,688 generated try-on images produced by 14 representative VTON models, together with 431,800 quality… See the full description on the dataset page: https://huggingface.co/datasets/zozonext/vtonqbench.