Combined Single and Multi-frame Image Super-resolution

摘要

Super-resolution (SR) is the process of obtaining a high-resolution (HR) image from one or more low-resolution (LR) images. Single-frame image super-resolution (SFISR) and multi-frame image super-resolution (MFISR) methods have been evolved independently for years. A neglected area in the field of SR is the combination of SFISR and MFISR. To fill this gap, we propose a novel optimization framework for using SFISR and MFISR simultaneously. Simulation results illustrate that our proposed method outperforms other benchmark SFISR and MFISR ones, both quantitatively and qualitatively.