Super-resolution reconstruction based on generative adversarial networks with dual branch half instance normalization

This paper proposes a super-resolution reconstruction model, SRPGANto improve the visual quality of images based on generative adversarial networks (GANs) by improving the network structures of the generator and the discriminator. In the generator, a dual branch residual block is designed instead of the residual block, including a branch with an attention mechanism and a branch without an attention mechanism, to extract more differentiated features. Normalization methods are explored to avoid unstable training and bath normalization artifacts and use a half instance normalization layer that is more suitable for underlying visual problems compared with traditional batch normalization. In the discriminator, PatchGAN is applied instead of typical GAN to improve the generation of local texture by discriminating each patch rather than the global image. The experimental results on the public datasets demonstrate that the proposed SRPGAN can achieve excellent quantitative evaluation while improving the visual quality of reconstructed images. A dual branch residual block (DBRB), which can extract more differentiated features and improve the feature extraction ability of RBs through a dual branch structure, and a dual branch half instance normalization block (DBHINB) by applying HIN to the proposed DBRB are proposed. Based on DBHINB, a super-resolution reconstruction model, SRPGAN is proposed based on generative adversarial networks, which can achieve excellent results in quantitative evaluation and image quality. image