Cross-layer Information Refining Network for Single Image Super-Resolution

Recently, deep learning-based image super-resolution (SR) has made a remarkable progress. However, previous SR methods rarely focus on the correlation between adjacent layers, which leads to underutilization of the information extracted by each convolutional layer. To address this problem, we design a simple and efficient cross-layer information refining network (CIRN) for single image super-resolution. Concretely, we propose the interlaced spatial attention block (ISAB) to measure the correlation between the adjacent layers feature maps and adaptively rescale spatial-wise features for refining the infromation. Owing to the two stage information propagation strategy, the ISAB can distill the primary information of adjacent layers without introducing too many parameters. Extensive experiments on benchmark datasets illustrate that our method achieves better accuracy than state-of-the-art methods even in 16× scale, specifically it has a better balance between performance and parameters.