AI 中文总结
该研究审计图像编辑器的模糊是否遵循薄透镜光学，通过渲染真值对比发现深度压缩和光圈响应衰减，且定性措辞影响显著。
AI 中文摘要
通用图像编辑器被要求使照片看起来像是在f/1.4光圈下拍摄的，但很少检查它们添加的模糊是否遵循薄透镜光学。物理光圈编辑以薄透镜比例在深度上分布模糊，并在光圈变化时改变模糊；先前的评估检查模糊单调性、锐度趋势相关性、有效光圈误差或视觉语言判断，而我们发现没有一项在已知深度下分别报告这两个属性。在这项针对两个编辑器（Gemini 3.1 Flash Image和GPT-image-2.5）的试点审计中，我们与渲染真值（oracle）进行比较：使用Blender Cycles场景，具有真实的薄透镜景深，一个模糊宽度估计器以相同方式应用于真值和编辑器输出，以及预注册的深度和光圈索引。在24个纹理场景中，使用一个三面板几何体渲染，可接受且可测量的面板显示f/1.4到f/2.8的宽度比，即$\bar\sigma_{1.4}/\bar\sigma_{2.8}$，为0.99--1.18，而真值为1.98--2.13；合并的中位数高斯等效近/远模糊宽度比约为1.18--1.25（Gemini）和0.97--1.05（GPT-image），而真值为1.69--1.82。预注册的黑盒干预表明，定性措辞改变模糊强度约2--10倍，而请求2像素与6像素则改变1.1--1.3倍，且没有测试的f-number措辞满足注册的“遵循”标准。深度压缩出现在原始和反转的中心聚焦布局中；当焦点在近面板时，可用面板深度索引达到注册阈值，而光圈响应在每种测试布局中保持衰减。从已发表方法改编的标量指标对压缩比例的合成编辑器给出类似真值的分数。
英文摘要
General image editors are asked to make a photo look as if it were taken at f/1.4, yet it is rarely checked whether the blur they add follows thin-lens optics. A physical aperture edit spreads blur across depth in thin-lens proportions and changes the blur when the aperture changes; prior evaluations check blur monotonicity, sharpness-trend correlation, effective-aperture error, or vision-language judgments, and none we found reports the two properties separately at known depths. In this pilot audit of two editors (Gemini~3.1 Flash Image and GPT-image-2.5) we compare against a rendered oracle: Blender Cycles scenes with true thin-lens depth of field, one blur-width estimator applied identically to oracle and editor outputs, and preregistered depth and aperture indices. In 24 texture scenes rendered in one three-panel geometry, accepted and measurable panels show f/1.4-to-f/2.8 width ratios, $\barσ_{1.4}/\barσ_{2.8}$, of 0.99--1.18 against 1.98--2.13 for the oracle, and ratios of pooled median Gaussian-equivalent near/far blur widths of about 1.18--1.25 (Gemini) and 0.97--1.05 (GPT-image) against 1.69--1.82. Preregistered black-box interventions show that qualitative wording changes blur strength by roughly 2--10 times, whereas a request for 2 versus 6 px changes it 1.1--1.3 times and no tested wording of the f-number meets the registered ``followed'' criterion. The depth compression appears in the original and reversed centre-focus layouts; with the focus on the near panel, the available-panel depth index reaches the registered threshold, and the aperture response stays attenuated in every layout tested. Scalar metrics adapted from published ones give oracle-like scores to synthetic editors whose proportions are compressed.
