Pyramidal dense attention networks for single image super-resolution

Abstract

Recently, residual and dense networks have effectively promoted the development of image super-resolution (SR). However, most dense networks based SR methods do not make full use of dense feature information. To solve this problem, a pyramidal dense attention network for single image super-resolution is proposed in this paper. In this method, the proposed pyramidal dense learning can gradually increase the width of the densely connected layer inside a pyramidal dense block to extract deep features efficiently. Meanwhile, the adaptive group convolution that the number of groups grows linearly with dense convolutional layers is introduced to relieve the parameter explosion. Besides, a novel joint attention to capture cross-dimension interaction between the spatial dimensions and channel dimension in an efficient way for providing rich discriminative feature representations is also proposed. Extensive experimental results show that the method achieves comparable performance in comparison with the state-of-the-art SR methods.