VTEdit-Bench：多参考图像编辑模型在虚拟试穿中的综合基准
VTEdit-Bench: A Comprehensive Benchmark for Multi-Reference Image Editing Models in Virtual Try-On
AI总结：
本文提出VTEdit-Bench基准，用于评估多参考图像编辑模型在虚拟试穿中的性能，包含24220对测试图像，涵盖五个代表性任务，通过VTEdit-QA评估模型一致性、布料一致性和图像质量。
摘要：
随着虚拟试穿（VTON）的持续发展，越来越多的现实场景涌现，推动了现有专门VTON模型的能力极限。同时，通用多参考图像编辑模型迅速发展，展现出强大的视觉编辑泛化能力，表明更灵活的VTON系统有前景。然而，尽管其能力强，通用编辑器在VTON中的优势和局限性仍因缺乏系统评估基准而未充分探索。为解决这一差距，我们引入VTEdit-Bench，一个全面的基准，用于评估通用多参考图像编辑模型在各种现实VTON场景中的表现。VTEdit-Bench包含24220对测试图像对，涵盖五个代表性VTON任务，具有逐步增加的复杂性，使系统分析鲁棒性和泛化能力成为可能。我们进一步提出VTEdit-QA，一种参考感知的VLM基于评估器，从三个关键方面评估VTON性能：模型一致性、布料一致性和整体图像质量。通过这一框架，我们系统评估了八个通用编辑模型，并将其与七个专门VTON模型进行比较。结果表明，顶级通用编辑器在传统任务中具有竞争力，并且更稳定地泛化到更难的场景，但在复杂的参考配置下仍面临挑战，特别是多布料条件。
英文摘要：
As virtual try-on (VTON) continues to advance, a growing number of real-world scenarios have emerged, pushing beyond the ability of the existing specialized VTON models. Meanwhile, universal multi-reference image editing models have progressed rapidly and exhibit strong generalization in visual editing, suggesting a promising route toward more flexible VTON systems. However, despite their strong capabilities, the strengths and limitations of universal editors for VTON remain insufficiently explored due to the lack of systematic evaluation benchmarks. To address this gap, we introduce VTEdit-Bench, a comprehensive benchmark designed to evaluate universal multi-reference image editing models across various realistic VTON scenarios. VTEdit-Bench contains 24,220 test image pairs spanning five representative VTON tasks with progressively increasing complexity, enabling systematic analysis of robustness and generalization. We further propose VTEdit-QA, a reference-aware VLM-based evaluator that assesses VTON performance from three key aspects: model consistency, cloth consistency, and overall image quality. Through this framework, we systematically evaluate eight universal editing models and compare them with seven specialized VTON models. Results show that top universal editors are competitive on conventional tasks and generalize more stably to harder scenarios, but remain challenged by complex reference configurations, particularly multi-cloth conditioning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
