A Matrix-in-matrix Neural Network for Image Super Resolution
This work addresses computational efficiency for practical image super-resolution applications, representing an incremental improvement over existing methods.
The paper tackles the problem of high computational requirements in deep learning methods for single image super-resolution by proposing a moderate-size network called MCAN that uses matrix ensembles of multi-connected channel attention blocks, achieving better performance with significantly fewer multiply-adds and parameters.
In recent years, deep learning methods have achieved impressive results with higher peak signal-to-noise ratio in single image super-resolution (SISR) tasks by utilizing deeper layers. However, their application is quite limited since they require high computing power. In addition, most of the existing methods rarely take full advantage of the intermediate features which are helpful for restoration. To address these issues, we propose a moderate-size SISR net work named matrixed channel attention network (MCAN) by constructing a matrix ensemble of multi-connected channel attention blocks (MCAB). Several models of different sizes are released to meet various practical requirements. Conclusions can be drawn from our extensive benchmark experiments that the proposed models achieve better performance with much fewer multiply-adds and parameters. Our models will be made publicly available.