Recent advances in diffusion models have led to a quantum leap in the quality of generative visual content. However, quantification of realism of the content is still challenging. Existing evaluation metrics, such as Inception Score and Fr\'echet inception distance, fall short on benchmarking diffusion models due to the versatility of the generated images. Moreover, they are not designed to quantify realism of an individual image. This restricts their application in forensic image analysis, which is becoming increasingly important in the emerging era of generative models. To address that, we first propose a metric, called Image Realism Score (IRS), computed from five statistical measures of a given image. This non-learning based metric not only efficiently quantifies realism of the generated images, it is readily usable as a measure to classify a given image as real or fake. We experimentally establish the model- and data-agnostic nature of the proposed IRS by successfully detecting fake images generated by Stable Diffusion Model (SDM), Dalle2, Midjourney and BigGAN. We further leverage this attribute of our metric to minimize an IRS-augmented generative loss of SDM, and demonstrate a convenient yet considerable quality improvement of the SDM-generated content with our modification. Our efforts have also led to Gen-100 dataset, which provides 1,000 samples for 100 classes generated by four high-quality models. We will release the dataset and code.

翻译：扩散模型的最新进展推动了生成视觉内容质量的巨大飞跃，但生成内容的真实性量化仍具挑战性。由于生成图像的多样性，现有评估指标如Inception Score（初始分数）和Fréchet Inception Distance（Fréchet初始距离）在扩散模型基准测试中存在不足。此外，这些指标无法量化单张图像的真实性，限制了它们在图像取证分析中的应用——这在生成模型新兴时代日益重要。为解决这一问题，我们首先提出一种名为图像真实性评分（IRS）的指标，该指标通过图像的五个统计指标计算得出。这种非基于学习的指标不仅能有效量化生成图像的真实性，还可直接作为区分图像真伪的度量。通过成功检测Stable Diffusion Model（SDM）、Dalle2、Midjourney和BigGAN生成的虚假图像，我们实验验证了所提IRS的模型无关性与数据无关性。我们进一步利用这一特性最小化SDM的IRS增强生成损失，通过改进显著提升了SDM生成内容的质量。此外，我们的工作还构建了Gen-100数据集，包含由四种高质量模型生成的100个类别各1,000个样本。数据集与代码将随文发布。