Image Super-Resolution Using Deep Convolutional Networks
Abstract¶
We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve trade-offs between performance and speed. Moreover, we extend our network to cope with three color channels simultaneously, and show better overall reconstruction quality.
Summary¶
SRCNN is the foundational deep-learning paper for single-image super-resolution, replacing hand-engineered sparse-coding pipelines with a direct end-to-end CNN mapping. Its simple architecture became the reference point that later fast, deep, residual, transformer, and diffusion super-resolution methods improve upon.