Image Super-Resolution Using Deep Convolutional Networks

This paper introduces a deep convolutional neural network (CNN) approach for single image super-resolution (SR). It learns the mapping between low-resolution and high-resolution images directly from data, avoiding hand-engineered features. The deep CNN is trained to reconstruct high-resolution images from their low-resolution counterparts, demonstrating superior performance compared to traditional SR methods in terms of accuracy and perceptual quality. This work laid the foundation for many subsequent deep learning-based SR techniques.