IEEE Trans Image Process. 2022;31:2279-2294. doi: 10.1109/TIP.2022.3154588. Epub 2022 Mar 15.
Numerous single image super-resolution (SISR) algorithms have been proposed during the past years to reconstruct a high-resolution (HR) image from its low-resolution (LR) observation. However, how to fairly compare the performance of different SISR algorithms/results remains a challenging problem. So far, the lack of comprehensive human subjective study on large-scale real-world SISR datasets and accurate objective SISR quality assessment metrics makes it unreliable to truly understand the performance of different SISR algorithms. We in this paper make efforts to tackle these two issues. Firstly, we construct a real-world SISR quality dataset (i.e., RealSRQ) and conduct human subjective studies to compare the performance of the representative SISR algorithms. Secondly, we propose a new objective metric, i.e., KLTSRQA, based on the Karhunen-Loéve Transform (KLT) to evaluate the quality of SISR images in a no-reference (NR) manner. Experiments on our constructed RealSRQ and the latest synthetic SISR quality dataset (i.e., QADS) have demonstrated the superiority of our proposed KLTSRQA metric, achieving higher consistency with human subjective scores than relevant existing NR image quality assessment (NR-IQA) metrics. The dataset and the code will be made available at https://github.com/Zhentao-Liu/RealSRQ-KLTSRQA.
近年来，已经提出了许多单幅图像超分辨率（SISR）算法，以便从低分辨率（LR）观测中重建高分辨率（HR）图像。然而，如何公平地比较不同 SISR 算法/结果的性能仍然是一个具有挑战性的问题。到目前为止，缺乏对大规模真实世界 SISR 数据集的全面人类主观研究和准确的客观 SISR 质量评估指标，使得无法真正了解不同 SISR 算法的性能。本文致力于解决这两个问题。首先，我们构建了一个真实世界的 SISR 质量数据集（即 RealSRQ），并进行了人类主观研究，以比较代表性的 SISR 算法的性能。其次，我们提出了一种新的基于 Karhunen-Loève 变换（KLT）的无参考（NR）客观度量 KLTSRQA，用于评估 SISR 图像的质量。在我们构建的 RealSRQ 和最新的合成 SISR 质量数据集（即 QADS）上的实验表明，我们提出的 KLTSRQA 度量具有优越性，与相关的现有 NR 图像质量评估（NR-IQA）度量相比，与人类主观评分具有更高的一致性。该数据集和代码将在 https://github.com/Zhentao-Liu/RealSRQ-KLTSRQA 上提供。
