Single image super-resolution (SISR) is a traditional image restoration problem. Given an image with low resolution (LR), the task\nof SISR is to find the homologous high-resolution (HR) image. As an ill-posed problem, there are works for SISR problem from\ndifferent points of view. Recently, deep learning has shown its amazing performance in different image processing tasks. There are\nworks for image super-resolution based on convolutional neural network (CNN). In this paper, we propose an adaptive residual\nchannel attention network for image super-resolution. We first analyze the limitation of residual connection structure and\npropose an adaptive design for suitable feature fusion. Besides the adaptive connection, channel attention is proposed to adjust the\nimportance distribution among different channels. A novel adaptive residual channel attention block (ARCB) is proposed in this\npaper with channel attention and adaptive connection. Then, a simple but effective upscale block design is proposed for different\nscales. We build our adaptive residual channel attention network (ARCN) with proposed ARCBs and upscale block. Experimental\nresults show that our network could not only achieve better PSNR/SSIM performances on several testing benchmarks but also\nrecover structural textures more effectively.
Loading....