MULTITEXTEDIT：跨语言文本-图像编辑中退化程度的基准测试
MULTITEXTEDIT: Benchmarking Cross-Lingual Degradation in Text-in-Image Editing
AI总结：
本文提出MULTITEXTEDIT基准测试，通过12种语言、5种视觉领域和7种编辑操作的3600个实例，评估跨语言文本-图像编辑中退化问题，引入语言保真度指标并发现模型在文本准确性和脚本保真度上的显著退化。
摘要：
文本-图像编辑已成为视觉内容创作的关键能力，但现有基准测试大多以英语为中心且常将视觉合理性与语义正确性混为一谈。我们引入MULTITEXTEDIT，一个包含3,600个实例的受控基准测试，涵盖12种语言类型、5种视觉领域和7种编辑操作。每个实例的语言变体共享相同的视觉基础，并配有人工编辑的参考文本和区域掩码，从而隔离语言变量以进行跨语言比较。为捕捉粗粒度文本匹配度指标所遗漏的脚本级错误，如缺失变音符号、RTL顺序颠倒和混合脚本渲染，我们引入了一个由两阶段LVM协议评分的语言保真度（LSF）度量，其与母语者标注员的二次加权κ值达到0.76。评估12个开源和专有系统时，发现所有模型在跨语言退化方面表现显著，最大退化出现在希伯来语和阿拉伯语上，最小退化出现在荷兰语和西班牙语上，且集中在文本准确性和脚本保真度而非粗粒度结构维度上。我们还发现普遍存在的语义和像素不匹配，其中输出保持全局布局和背景保真度，但扭曲了脚本特定的形态。
英文摘要：
Text-in-image editing has become a key capability for visual content creation, yet existing benchmarks remain overwhelmingly English-centric and often conflate visual plausibility with semantic correctness. We introduce MULTITEXTEDIT, a controlled benchmark of 3,600 instances spanning 12 typologically diverse languages, 5 visual domains, and 7 editing operations. Language variants of each instance share a common visual base and are paired with a human-edited reference and region masks, isolating the language variable for cross-lingual comparison. To capture script-level errors that coarse text-matching metrics miss, such as missing diacritics, reversed RTL order, and mixed-script renderings, we introduce a language fidelity (LSF) metric scored by a two-stage LVM protocol that first traces the edited target text and then judges it in isolation, reaching a quadratic-weighted \k{appa} of 0.76 against native-speaker annotators. Evaluating 12 open-source and proprietary systems with LSF alongside standard semantic and mask-aware pixel metrics, we find pronounced cross-lingual degradation for every model, largest on Hebrew and Arabic and smallest on Dutch and Spanish, and concentrated in text accuracy and script fidelity rather than in coarse structural dimensions. We also uncover a pervasive semantic and pixel mismatch, where outputs preserve global layout and background fidelity yet distort script-specific forms.
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。
