Image super-resolution method and device based on VDSR model applying novel ReLU function, and storage medium

The invention relates to an image super-resolution method and device based on a VDSR model applying a novel ReLU function and a storage medium. The method comprises the steps: inputting a to-be-processed image into a trained improved VDSR model, and outputting the to-be-processed image to obtain a high-resolution image of the to-be-processed image; wherein a novel ReLU function in the improved VDSR model is a ReLU function for self-adaptively learning a static working point; under the inspiration of a triode amplifying circuit, the concept of a static working point is introduced into a novel ReLU function, a zero point in a traditional ReLU function serves as the static working point, and the value of the static working point is learned in a self-adaptive mode in the neural network training process. A novel ReLU function is applied to a VDSR model, and a data augmentation and learning rate attenuation strategy is adopted in the network training process, so that an over-fitting phenomenon of the network is avo