Research on Super-Resolution Enhancement Algorithm Based on Skip Residual Dense Network
Shaoshuo Mu, Zhang Yan-hua, Xiaolan Qian, Yanbing Jiang · 2021
In this paper, a super-resolution enhancement model based on skip residual dense net(SRDN) is proposed. We design a model with a two-channel skip residual dense nets to extract deeper feature information. The two channels have the same network structure and are connected by skip connections. The model first divide the input image into two components by a guided filtering. The features of two components is learned by one convolution layer and a three layers double-channel SRDN network respectively. Then model uses the concatenation operation to combine two channels’ feature. Finally, the super-resolution image is obtained by the up-sampling network and one convolution operation. Different to the classical loss function, we define a joint loss functions for training, which is consisted of content loss, perceptual loss and color discrimination loss. The experimental results show that the proposed algorithm achieves better super-resolution visual results ans objective evaluation indicators.