Deformable and residual convolutional network for image super-resolution

Recent research on image super-resolution (SR) has greatly progressed with the development of convolutional neural networks (CNNs). However, the fixed geometric structures of standard convolution filters largely limit the learning capacity of CNNs for image SR. To effectively address this problem, we propose a deformable and residual convolutional network (DefRCN) for image SR. Specifically, a deformable residual convolution block (DRCB) is developed to augment spatial sampling locations and enhance the transformation modelling capability of CNNs. In addition, we optimize the residual convolution block to reduce the model redundancy and alleviate the vanishing-gradient in backpropagation. In addition, the proposed upsample block allows the network to directly process low-resolution images, which reduces the computational resource cost. Extensive experiments on benchmark datasets verify that the proposed method achieves a high quantitative and qualitative performance.