DGRN: Image super-resolution with dual gradient regression guidance

In single image super-resolution (SISR), deep neural networks learn mainly nonlinear functions to obtain promising high-resolution (HR) images. However, there are usually two undesired limitations to recovered images of existing SR methods. First, since this task is typically an ill-posed problem, recovering the structural information for the SR process is usually sharp edges but distorted. Second, since this task generally has an extremely large space for the mapping function, learning this mapping from low-resolution (LR) to HR images is typically difficult. For the most part, SR models usually suffer from the lack of structural information for the objects in images and poor performance. To address the above issues, we propose a dual gradient regression scheme in the first stage of the network to recover the structure information of objects in images and the corresponding loss function to learn the difference between structural maps. In the second stage of the network, we restore HR gradient maps by the first stage to provide additional structural information for the second stage, further constraining the structure of the SR image and reducing the space of the possible functions. Extensive experiments demonstrate our results outperform the state-of-the-art SR methods in the SSIM, and achieve better visual effects than the state-of-the-art SR methods.(c) 2022 Published by Elsevier Ltd.

Automated summary

In this paper, a dual gradient regression scheme is proposed to improve the image restoration problem of existing super-resolution methods. In the first stage of the network, the proposed scheme is used to recover the structural information of the image and learn the difference between structural maps. In the second stage, the HR gradient maps restored by the first stage are used to provide additional structural information and further constrain the structure of the SR image. Experimental results show that the proposed method outperforms the state-of-the-art SR methods in terms of SSIM and visual effects.