Distorted image reconstruction method based on deep learning and related device

The invention discloses a distorted image reconstruction method based on deep learning and a related device, and the method comprises the steps: constructing a distorted image reconstruction training set according to a high-definition image set, and the distorted image reconstruction training set comprises a preset distorted image and a corresponding preset image reconstruction matrix; network layer gradient iterative training is carried out on the initial DFISTA network model by using the distorted image reconstruction training set to obtain a preset DFISTA network model, and the initial DFISTA network model is constructed according to an FISTA algorithm and a deep neural network; and performing image reconstruction on the current distorted image through a preset DFISTA network model to obtain a distorted image reconstruction matrix. The model is trained in a gradient iteration mode, the accuracy and reliability of the model can be ensured, and the convergence speed of the model can be increased. Therefore,