DPGF-Net：用于联合评估 AI 生成图像感知质量与语义一致性的双先验引导融合网络
DPGF-Net: Dual-Prior Guided Fusion Network for Joint Assessment of Perceptual Quality and Semantic Consistency in AI-Generated Images
面向 AI 生成图像的联合质量与语义一致性评估，用图像侧先验把渲染失真与内容解耦、再与提示词模板交互，可作为 T2I 生成模型评测与数据筛选的自动化打分器。
原文依据 disentangling image content and rendering distortions is vital
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论AI 生成技术的发展需要有效的图像质量评估（AGIQA）方法来联合评估视觉质量与文本内容对齐程度，从而确保生成内容既在视觉上具有吸引力，又忠实于用户的指令。然而，视觉退化与文本内容失配往往同时出现，难以判断一次较差的主观评价究竟源于提示词不遵循还是渲染伪影。因此，将图像内容与渲染失真解耦至关重要。我们提出双先验引导融合网络（DPGF-Net），它利用图像侧先验从内容中解耦失真，并将其与文本侧提示词模板相结合以模拟二者的交互，从而解决该问题。DPGF-Net 采用局部文本条件聚合分支来突出语义相关且对质量敏感的区域，并结合捕获整体感知特性的全局调制分支。最后，自适应融合产生单一分数。在三个 AGIQA 数据集上的实验表明，我们的方法与人主观判断高度相关，具有更低的预测误差和稳定的评估行为。源代码见 https://github.com/leeto221/AGIQA。
英文原文摘要 1289 字符
The development of AI-generated technology requires effective image quality assessment (AGIQA) methods to jointly evaluate visual quality and text-content alignment, ensuring that the generated content is both visually appealing and faithful to the user's instructions. Nevertheless, visual degradation and text-content misalignment often coincide, and it is difficult to tell whether a bad subjective evaluation arises from prompt noncompliance or rendering artifacts. As such, disentangling image content and rendering distortions is vital. We propose the dual-prior guided fusion network (DPGF-Net), which leverages image-side priors to disentangle distortions from content and combines them with text-side prompt templates to simulate their interactions, to address this issue. DPGF-Net employs a local text-conditioned aggregation branch to highlight semantically relevant and quality-sensitive regions in conjunction with a global modulation branch that captures holistic perceptual characteristics. Finally, adaptive fusion produces a single score. Experiments on three AGIQA datasets demonstrate that our method is highly correlated with human judgments, with lower prediction error and stable evaluation behavior. The source code is available at https://github.com/leeto221/AGIQA.