Single image super-resolution with multi-scale information cross-fusion network

Abstract

The deep convolutional neural networks have achieved significant improvements in terms of effectiveness and efficiency for single image super-resolution. However, as the depth of neural network grows, the information flow is weakened. On the other hand, most of the models adopt a single-stream structure with which integrating complementary information under different receptive fields is difficult. To improve information flow and capture sufficient knowledge for reconstructing high-frequency details, we propose a multi-scale information cross-fusion network (MSICF) in which a sequence of subnetworks is cascaded to infer high resolution features in a coarse-to-fine manner. In each cascaded subnetwork, we stack multiple multi-scale cross (MSC) modules to fuse multi-scale complementary information in an efficient way as well as to improve information flow across the layers. Meanwhile, by introducing residual-feature learning in each stage, the relative information between features at different levels is fully utilized to further boost reconstruction performance. We train the proposed network with cascaded-supervision and then assemble the intermediate predictions of the cascade to achieve high quality image. Extensive quantitative and qualitative evaluations on benchmark datasets illustrate the superiority of our proposed method over state-of-the-art super-resolution methods.