In comparison with the generation of monoscopic images, the time cost of rendering stereoscopic images is doubled. When generating stereoscopic images by computer algorithms, it is desirable to save the computational expense by decreasing the image resolution, without degrading the visual perceptual quality of the images. In this work, to evaluate the perceptual visual quality of computer-generated stereoscopic images (CGSIs), a data set consisting of stereoscopic images created with different horizontal and vertical resolutions was constructed. First, a series of subjective experiments for the analysis of various perceptual situations was conducted. The experimental results show that when the original image resolution was reduced by half, the image difference was not perceptible. In addition, based on full-reference (FR) and no-reference (NR) image quality measurement (IQM), a combined FR-and-NR CGSIQA model was established to predict perceptual quality. We perform weighting calculations for different combinations of FR and NR. The experimental results show that the proposed model significantly outperforms all the classical models.

与单视场图像的生成相比，渲染立体图像的时间成本增加了一倍。当通过计算机算法生成立体图像时，期望通过降低图像分辨率来节省计算费用，而不会降低图像的视觉感知质量。在这项工作中，为了评估计算机生成的立体图像（CGSI）的感知视觉质量，构建了一个由具有不同水平和垂直分辨率的立体图像组成的数据集。首先，进行了一系列主观实验，以分析各种感知情况。实验结果表明，当原始图像分辨率降低一半时，图像差异是不可察觉的。此外，基于全参考（FR）和无参考（NR）图像质量测量（IQM），建立了FR和NR CGSIQA组合模型来预测感知质量。我们对FR和NR的不同组合执行加权计算。实验结果表明，所提出的模型明显优于所有经典模型。