SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks
This work addresses efficiency issues in single image super-resolution for computer vision applications, but it is incremental as it builds on existing squeeze and excitation and recursive techniques.
The authors tackled the problem of high computational cost in deep super-resolution models by proposing SESR, a method using recursive squeeze and excitation networks, which achieved state-of-the-art speed and accuracy on four benchmark datasets.
Single image super resolution is a very important computer vision task, with a wide range of applications. In recent years, the depth of the super-resolution model has been constantly increasing, but with a small increase in performance, it has brought a huge amount of computation and memory consumption. In this work, in order to make the super resolution models more effective, we proposed a novel single image super resolution method via recursive squeeze and excitation networks (SESR). By introducing the squeeze and excitation module, our SESR can model the interdependencies and relationships between channels and that makes our model more efficiency. In addition, the recursive structure and progressive reconstruction method in our model minimized the layers and parameters and enabled SESR to simultaneously train multi-scale super resolution in a single model. After evaluating on four benchmark test sets, our model is proved to be above the state-of-the-art methods in terms of speed and accuracy.