Image super-resolution reconstruction method based on high-frequency information feature fusion

The invention discloses an image super-resolution reconstruction method based on high-frequency information feature fusion, which constructs a generative network and comprises a feature pre-extraction module, a residual network, an up-sampling module and an output module. Pre-training the generative network by using the training image set to obtain a generative network pre-training model; a generative adversarial network based on high-frequency information feature fusion is constructed, the generative adversarial network comprises a generative network and a discrimination network, the generative network loads a generative network pre-training model, and the discrimination network is composed of a high-frequency information distillation module, a high-frequency information feature extraction module, an image feature extraction module, a feature fusion module and a pixel domain discrimination module; performing adversarial training on the generative network and the discriminant network by using the training ima