IEEE Trans Pattern Anal Mach Intell. 2018 Sep;40(9):2180-2193. doi: 10.1109/TPAMI.2017.2747150. Epub 2017 Aug 30.
Visual realism is defined as the extent to which an image appears to people as a photo rather than computer generated. Assessing visual realism is important in applications like computer graphics rendering and photo retouching. However, current realism evaluation approaches use either labor-intensive human judgments or automated algorithms largely dependent on comparing renderings to reference images. We develop a reference-free computational framework for visual realism prediction to overcome these constraints. First, we construct a benchmark dataset of 2,520 images with comprehensive human annotated attributes. From statistical modeling on this data, we identify image attributes most relevant for visual realism. We propose both empirically-based (guided by our statistical modeling of human data) and deep convolutional neural network models to predict visual realism of images. Our framework has the following advantages: (1) it creates an interpretable and concise empirical model that characterizes human perception of visual realism; (2) it links computational features to latent factors of human image perception.
视觉逼真度定义为图像在人们眼中看起来像照片而不是计算机生成的程度。评估视觉逼真度在计算机图形渲染和照片修饰等应用中非常重要。然而，当前的真实感评估方法要么使用劳动密集型的人工判断，要么主要依赖于将渲染与参考图像进行比较的自动化算法。我们开发了一种无参考的计算框架，用于视觉逼真度预测，以克服这些限制。首先，我们构建了一个包含 2520 张图像的基准数据集，这些图像具有全面的人工注释属性。通过对这些数据的统计建模，我们确定了对视觉逼真度最相关的图像属性。我们提出了基于经验的（由我们对人类数据的统计建模指导）和深度卷积神经网络模型来预测图像的视觉逼真度。我们的框架具有以下优势：（1）它创建了一个可解释的、简洁的经验模型，描述了人类对视觉逼真度的感知；（2）它将计算特征与人类图像感知的潜在因素联系起来。
