无需真实参考图，用真人评价数据评估虚拟试衣质量。
Reference-Free Image Quality Assessment for Virtual Try-On via Human Feedback
- 构建真人标注的试衣图像质量数据集，模拟人类感知判断。
- 在6万张试衣图上验证，模型评估结果与真人评分高度一致。
- 适合评估虚拟试衣系统性能，尤其缺乏真实参考图的场景。
随着虚拟试衣（VTON）系统在时尚电商中的重要性提升，实际场景中往往无法获取同一人穿着目标服装的真实参考图像，因此亟需可靠的无参考评估方法。为此，我们提出VTON-IQA，一种无需真实图像即可实现人类对齐的图像质量评估框架。为建模人类感知判断，我们构建了VTON-QBench，一个大规模真人标注基准，包含14个代表性VTON模型生成的62,688张试衣图像，以及来自13,838名合格标注者收集的431,800条质量评分。据我们所知，这是目前最大的用于VTON领域人类主观评价的数据集。大量实验表明，VTON-IQA能可靠地实现与人类评价一致的质量评估。此外，我们还利用VTON-IQA对14个典型VTON模型进行了全面基准评测。
原文摘要 · Abstract (English)
As virtual try-on (VTON) systems become increasingly important in fashion e-commerce, there is a growing need for reliable reference-free evaluation methods, since ground-truth images of the same person wearing the target garment are typically unavailable in real-world scenarios. To address this challenge, we propose VTON-IQA, a reference-free framework for human-aligned image quality assessment without requiring ground-truth images. To model human perceptual judgments, we construct VTON-QBench, a large-scale human-annotated benchmark comprising 62,688 try-on images generated by 14 representative VTON models and 431,800 quality annotations collected from 13,838 qualified annotators. To the best of our knowledge, this is the largest dataset to date for human subjective evaluation in VTON. Extensive experiments show that VTON-IQA achieves reliable human-aligned image quality assessment. Moreover, we conduct a comprehensive benchmark evaluation of 14 representative VTON models using VTON-IQA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。