TY - JOUR N2 - To better extract feature maps from low-resolution (LR) images and recover high-frequency information in the high-resolution (HR) images in image super-resolution (SR), we propose in this paper a new SR algorithm based on a deep convolutional neural network (CNN). The network structure is composed of the feature extraction part and the reconstruction part. The extraction network extracts the feature maps of LR images and uses the sub-pixel convolutional neural network as the up-sampling operator. Skip connection, densely connected neural networks and feature map fusion are used to extract information from hierarchical feature maps at the end of the network, which can effectively reduce the dimension of the feature maps. In the reconstruction network, we add a 3×3 convolution layer based on the original sub-pixel convolution layer, which can allow the reconstruction network to have better nonlinear mapping ability. The experiments show that the algorithm results in a significant improvement in PSNR, SSIM, and human visual effects as compared with some state-of-the-art algorithms based on deep learning. L1 - http://www.czasopisma.pan.pl/Content/121550/PDF/1949_corr.pdf L2 - http://www.czasopisma.pan.pl/Content/121550 PY - 2022 IS - 1 EP - e139616 DO - 10.24425/bpasts.2021.139616 KW - super-resolution KW - convolutional neural network KW - sub-pixel convolutional neural network KW - densely connected neural networks A1 - Yang, Xin A1 - Zhang, Yifan A1 - Zhou, Dake VL - 70 DA - 25.02.2022 T1 - Deep networks for image super-resolution using hierarchical features SP - e139616 UR - http://www.czasopisma.pan.pl/dlibra/publication/edition/121550 T2 - Bulletin of the Polish Academy of Sciences Technical Sciences ER -