Lightweight Image Super-Resolution via Weighted Multi-Scale Residual Network

The tradeoff between efficiency and model size of the convolutional neural network (CNN) is an essential issue for applications of CNN-based algorithms to diverse real-world tasks. Although deep learning-based methods have achieved significant improvements in image super-resolution (SR), current CNN-based techniques mainly contain massive parameters and a high computational complexity, limiting their practical applications. In this paper, we present a fast and lightweight framework, named weighted multi-scale residual network (WMRN), for a better tradeoff between SR performance and computational efficiency. With the modified residual structure, depthwise separable convolutions (DS Convs) are employed to improve convolutional operations' efficiency. Furthermore, several weighted multi-scale residual blocks (WMRBs) are stacked to enhance the multi-scale representation capability. In the reconstruction subnetwork, a group of Conv layers are introduced to filter feature maps to reconstruct the final high-quality image. Extensive experiments were conducted to evaluate the proposed model, and the comparative results with several state-of-the-art algorithms demonstrate the effectiveness of WMRN.

Automated summary

In this paper, a fast and lightweight framework named weighted multi-scale residual network (WMRN) is proposed for a better tradeoff between image super-resolution performance and computational efficiency. The network utilizes depthwise separable convolutions and weighted multi-scale residual blocks to improve efficiency and multi-scale representation capability, with Convolutional layers in the reconstruction subnetwork to filter feature maps for high-quality image reconstruction. Extensive experiments show the effectiveness of WMRN compared to several state-of-the-art algorithms.