Image Processing Method, Electronic Device and Non-Transient Computer Readable Medium

An image processing method, comprising:

• performing detail enhancement on an input image to be processed to obtain an output image by using a trained multi-scale detail enhancement model;
• wherein the multi-scale detail enhancement model is configured to perform following acts:
• performing a multi-scale decomposition on the input image to obtain a base layer image and at least one detail layer image of the input image;
• acquiring a first feature map of the base layer image and acquiring a second feature map of each of the detail layer images;
• acquiring a first residual feature corresponding to the first feature map, and acquiring a second residual feature corresponding to the second feature map of each of the detail layer images;
• obtaining a base layer output image according to the first residual feature, each of the second residual features and the first feature map, and for each of the detail layer images, obtaining a detail layer output image corresponding to the detail layer image according to the first residual feature, each of the second residual features and the second feature map of the detail layer image;
• and
• performing an image fusion on the base layer output image and each of the detail layer output images to obtain the output image.