Image Super-Resolution Method Based on Dual Learning

Abstract

Existing super-resolution methods convert high-resolution images into low-resolution images, and use the synthesized images as input to train the model. However, it is difficult for synthetic low-resolution images to reflect the characteristics of real low-resolution images, resulting in poor model performance in practical applications. To address this problem, we propose a recurrent super-resolution framework, which consists of a degradation model and a reconstruction model. The degradation model degenerates the real high-resolution image into a more real low-resolution image, which is used as the input of the super-resolution reconstruction network, and then uses the reconstruction model to reconstruct the low-resolution image, and calculates the error with the original image. The generated high-resolution image is input into the degradation model again for degradation processing, forming a symmetrical and cyclic network structure, so that the super-resolution model has a better effect when reconstructing the real low-scoring image. In addition, the spatial attention mechanism is introduced into the generator network, which expands the receptive field of the convolution kernel, better extracts long-distance image features and improves the texture details of super-resolution images, which is consistent with the global.