Single-Image Super-Resolution: A Benchmark

Abstract. Single-image super-resolution is of great importance for vi-sion applications, and numerous algorithms have been proposed in recent years. Despite the demonstrated success, these results are often gener-ated based on different assumptions using different datasets and met-rics. In this paper, we present a systematic benchmark evaluation for state-of-the-art single-image super-resolution algorithms. In addition to quantitative evaluations based on conventional full-reference metrics, hu-man subject studies are carried out to evaluate image quality based on visual perception. The benchmark evaluations demonstrate the perfor-mance and limitations of state-of-the-art algorithms which sheds light on future research in single-image super-resolution