Single image super-resolution using a polymorphic parallel CNN

In recent years, artificial intelligence has drawn the attention of the world, and the contributions of deep learning is enormous. The convolution neural network (CNN) provides more opportunities and better choices for our work. This paper explores the potential of deep neural networks in single image super-resolution (SR). In fact, some models based on deep neural networks have achieved remarkable performance in the reconstruction accuracy of individual images, but there is more room for development. In this paper, we removed the bicubic interpolation operation which is handcraft up-sampling and not intelligent enough. And we introduced deconvolution layer instead of up-sampling layer. In addition, we designed the local polymorphic parallel network and many-to-many connections. On the basis of this theory, we have carried out a simulation experiment to prove the excellent effectiveness of the proposed method.