超分辨图像质量评价综述

全面综述了超分辨图像质量评价的研究进展。超分辨图像质量评价是以人眼的主观质量评价结果为依据，利用算法模型对重建的超分辨图像进行评价。该评价方法对超分辨重建算法的优化和模型参数的选择具有重要的指导意义。首先对超分辨图像的主观评价方法进行阐述；其次对现有超分辨图像客观评价方法按照全参考型、部分参考型和无参考型进行了分类阐述，特别详细介绍了几种具有代表性的无参考质量评价的主要思想；接着从定量和定性两方面分别介绍了评价超分辨图像质量评价方法有效性的指标，并对评价算法的主要实验方法进行了简要阐述；最后对超分辨图像质量评价方法未来的发展趋势进行了展望。

Survey of Super-Resolution Images Quality Assessment

This paper comprehensively surveys the development of Super-Resolution Image Quality Assessment（SRIQA）. The objective of SRIQA is to design a computational model to measure the perceptual quality of Super-Resolution（SR） images based on the statistical results of subjective quality assessment. The SRIQA methods are significantly instructive for the optimization and the parameters selection of SR algorithms. First, this paper presents the subjective evaluation method for SR images. Next according to the categories of Full-Reference（FR）, Reduced-Reference（RR）, and No-Reference（NR） quality assessment methods, the existing objective quality assessment methods for SR images are introduced, respectively. Particularly, the major idea of NR quality assessment algorithms is presented in detail. Then the quantitative and qualitative evaluation indexes for SRIQA methods are provided, and the main experimental approaches for evaluating the effectiveness of the SR algorithms are described. Finally, the development trends of SRIQA are summarized.