Image Super-Resolution Based on Dual Path Network

Recently, Convolutional Neural Network (CNN) based methods have demonstrated high-quality reconstruction for Single Image Super-Resolution (SISR). Particularly, residual learning shows improved performance. For the SR reconstruction performance of the CNN-based models, the design of model architecture is very important. In this paper, we present SRDPN, a super-resolution network based on Dual Path Network (DPN). The DPN combines the advantages of the state-of-the-art Residual Network (ResNet) and Dense Convolutional Network (DenseNet), which enjoys lower computational cost, lower memory consumption and higher parameter efficiency. Extensive qualitative and quantitative evaluations on benchmark datasets show that our proposed method performs better than the state-of-the-art methods in terms of peak signal-to-noise ratio (PSNR) and image quality.