Image Super-Resolution Using Deep Convolutional Networks

This paper introduces a deep convolutional neural network (CNN) approach for single image super-resolution (SR). The method directly learns a mapping between low-resolution and high-resolution images, using a deep network to capture the complex relationships. By training a CNN to predict high-resolution image patches from low-resolution inputs, the method achieves state-of-the-art SR performance with significant improvements in accuracy and speed compared to traditional methods.