METHOD FOR TRAINING IMAGE PROCESSING MODEL, IMAGE PROCESSING METHOD, NETWORK DEVICE, AND STORAGE MEDIUM

A method for training an image processing model for processing a blurred image, an image processing method, and a network device. The image processing model at least comprises a first network and a second network. The training method comprises: obtaining a sample pair for training (S301), the sample pair comprising a clear image and a blurred image; invoking an image processing model to perform definition restoration processing on the blurred image to obtain a restored image (S302); and updating, according to the restored image and the clear image, a network parameter of a first network and/or a network parameter of a second network in the image processing model (S303) to obtain a trained image processing model, wherein the network parameter of the first network and the network parameter of the second network satisfy a selective sharing condition, and the selective sharing condition is used for indicating a network parameter for sharing between the first network and the second network and a network parameter for mutual independence between the first network and the second network.