Towards realistic image via function learning

There has been a remarkable growth in computer vision due to the introduction of deep convolutional neural network. In most electronic imaging applications, images with high resolution are desired and cannot be ignored in many crucial applications. Super-resolution is a technique that enhances the resolution of images from the low-resolution input. Even thought, the performance of pattern recognition in computer vision will be improved if high resolution image is provided. The current super-resolution models based convolutional neural network has shown great performance, and also could outpace the other models. Depth in of CNN models is crucial importance for image super-resolution. However, the deeper networks based SR techniques are more difficult to train. To address these problems we propose a very deep residual network which comprises residual in residual structure to form a very deep network. In particular, the proposed model consists of several residual units with long skip connection. The proposed model allows low-frequency information to be bypassed through multiple skip connections, and the high-frequency information will be centralized in the main network. Extensive experiments show that our proposed model achieves better performance against state-of-the-art methods.