Multi-level U-net network for image super-resolution reconstruction

• Developed a multi-level back projection residual network (MBRN) for super-resolution. • Designed a U-Net back projection structure to keep the feature map size constant. • Designed a multi-level back projection structure to extract high-frequency and low-frequency information. Deep neural networks have shown better effects for super-resolution. However, it is difficult to extract multi-level features of LR images to reconstruct more clear images. To solve this problem, we present a multi-level U-Net network (MUN) for image super-resolution reconstruction. Specifically, we present a multi-level U-Net residual structure, which is composed of two different levels U-Net structures, to extract multi-level features of LR images. Meanwhile, we present a multi-scale residual block, which extracts multi-level features by dual-branch convolutional layers with different kernels and uses long and short skip connections to bypass a large amount of low-frequency information. Extensive experimental results demonstrate that our presented MUN outperforms other state-of-the-art super-resolution methods.