Blind Visual Quality Assessment for Super-Resolution Images: Database and Model

Image super-resolution (SR) algorithms are placed on high hope to reconstruct ultra-high-definition (UHD) videos from existing low-resolution videos. Efficient image quality assessment (IQA) methods could not only evaluate the performances of SR algorithms but also provide reliable feedback for algorithm optimization. However, only a few IQA databases and metrics have been specially designed for SR images. In this paper, we propose a database SR4KIQA containing 4K pristine images and super-resolution 4K distorted images with mean opinion score (MOS) labels. Distorted SR images are generated by five classic interpolation methods and seven typical DNN-based super-resolution algorithms. Then, a large-scale database SR4K298 owning 16688 pairs of SR distorted images is designed to support the training process of the ranking-based blind image quality assessment (BIQA) metric we proposed. SROCC of our metric Rank-SR has already reached 0.87 on the SR4KIQA database before the fine-tuning, which outperforms the state-of-art IQA metrics. As one of the very first IQA databases for 4K SR images artifacts, our database SR4KIQA has been publicly available on http://www.dx.doi.org/10.11922/sciencedb.00806 to encourage the further study of the research community.