MobileSR: Efficient Convolutional Neural Network for Super-resolution

The existing deep CNN models on single image super-resolution processing are computationally-intensive in terms of memory usage and training time. In resources-limited platforms, it is desirable to consider developing light-weight models for super-resolution tasks. This paper proposes a parallel-group convolution, which uses 25% computation of the standard convolutions. With parallel-group convolutions, we develop an efficient light-weight convolutional neural network named MobileSR for super-resolution. Experimental results show that our proposed method achieves appreciable improvements over the state-of-the-art models with approximately 75% size reduction. The source code is available at https://github.com/DestinyK/MobileSR.