Optimization of Single Image Super-Resolution Reconstruction Algorithm Based on Residual Dense Network

摘要

Aiming at the problem of low performance of the Single Image Super-Resolution (SISR) method, a method based on residual dense network is proposed. The shallow convolution features are input to the residual dense block to obtain local and global features, and the reconstruction is performed on the images to obtain a clear high-resolution image. To verify the effectiveness of the method, quantitative experiments were performed on three public datasets including Set5, Set14 and B100. Experimental results show that this method can better recover high-resolution images.