VTBench: Comprehensive Benchmark Suite Towards Real-World Virtual Try-on Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiaobin, Hu, Yujie, Liang, Donghao, Luo, Xu, Peng, Jiangning, Zhang, Junwei, Zhu, Chengjie, Wang, Yanwei, Fu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915305194782720
author Xiaobin, Hu
Yujie, Liang
Donghao, Luo
Xu, Peng
Jiangning, Zhang
Junwei, Zhu
Chengjie, Wang
Yanwei, Fu
author_facet Xiaobin, Hu
Yujie, Liang
Donghao, Luo
Xu, Peng
Jiangning, Zhang
Junwei, Zhu
Chengjie, Wang
Yanwei, Fu
contents While virtual try-on has achieved significant progress, evaluating these models towards real-world scenarios remains a challenge. A comprehensive benchmark is essential for three key reasons:(1) Current metrics inadequately reflect human perception, particularly in unpaired try-on settings;(2)Most existing test sets are limited to indoor scenarios, lacking complexity for real-world evaluation; and (3) An ideal system should guide future advancements in virtual try-on generation. To address these needs, we introduce VTBench, a hierarchical benchmark suite that systematically decomposes virtual image try-on into hierarchical, disentangled dimensions, each equipped with tailored test sets and evaluation criteria. VTBench exhibits three key advantages:1) Multi-Dimensional Evaluation Framework: The benchmark encompasses five critical dimensions for virtual try-on generation (e.g., overall image quality, texture preservation, complex background consistency, cross-category size adaptability, and hand-occlusion handling). Granular evaluation metrics of corresponding test sets pinpoint model capabilities and limitations across diverse, challenging scenarios.2) Human Alignment: Human preference annotations are provided for each test set, ensuring the benchmark's alignment with perceptual quality across all evaluation dimensions. (3) Valuable Insights: Beyond standard indoor settings, we analyze model performance variations across dimensions and investigate the disparity between indoor and real-world try-on scenarios. To foster the field of virtual try-on towards challenging real-world scenario, VTBench will be open-sourced, including all test sets, evaluation protocols, generated results, and human annotations.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19571
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VTBench: Comprehensive Benchmark Suite Towards Real-World Virtual Try-on Models
Xiaobin, Hu
Yujie, Liang
Donghao, Luo
Xu, Peng
Jiangning, Zhang
Junwei, Zhu
Chengjie, Wang
Yanwei, Fu
Computer Vision and Pattern Recognition
While virtual try-on has achieved significant progress, evaluating these models towards real-world scenarios remains a challenge. A comprehensive benchmark is essential for three key reasons:(1) Current metrics inadequately reflect human perception, particularly in unpaired try-on settings;(2)Most existing test sets are limited to indoor scenarios, lacking complexity for real-world evaluation; and (3) An ideal system should guide future advancements in virtual try-on generation. To address these needs, we introduce VTBench, a hierarchical benchmark suite that systematically decomposes virtual image try-on into hierarchical, disentangled dimensions, each equipped with tailored test sets and evaluation criteria. VTBench exhibits three key advantages:1) Multi-Dimensional Evaluation Framework: The benchmark encompasses five critical dimensions for virtual try-on generation (e.g., overall image quality, texture preservation, complex background consistency, cross-category size adaptability, and hand-occlusion handling). Granular evaluation metrics of corresponding test sets pinpoint model capabilities and limitations across diverse, challenging scenarios.2) Human Alignment: Human preference annotations are provided for each test set, ensuring the benchmark's alignment with perceptual quality across all evaluation dimensions. (3) Valuable Insights: Beyond standard indoor settings, we analyze model performance variations across dimensions and investigate the disparity between indoor and real-world try-on scenarios. To foster the field of virtual try-on towards challenging real-world scenario, VTBench will be open-sourced, including all test sets, evaluation protocols, generated results, and human annotations.
title VTBench: Comprehensive Benchmark Suite Towards Real-World Virtual Try-on Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.19571