MULTI-LEVEL RESIDUAL UP-PROJECTION ACTIVATION NETWORK FOR IMAGE SUPER-RESOLUTION

Although convolutional neural networks (CNNs) have received great attention in image super-resolution (SR), most SR networks do not take full account of the hierarchical features of the original low-resolution (LR) images, including the spatial feature information and the channel-wise feature information. To solve this problem, we propose a multi-level residual up-projection activation network (MRUAN) consisting of residual up-projection group (RUG), upscale module and residual activation block (RAB). Specifically, RUG uses recursive method to mine hierarchical LR feature information and HR residual information. Subsequently, the upscale module adopts multi-level LR feature information as input to obtain HR features. Furthermore, we improve the original residual block with spatial-and-channel attention mechanism, which adaptively recalibrates features by considering the spatial relationships within channel and the pixel-wise inter-dependencies between channels simultaneously. Experiments on benchmark datasets show that our MRUAN achieves favorable performance against state-of-the-art methods.