Model training method, super-resolution reconstruction method, device, equipment and medium

Abstract

The invention discloses a model training method and device, a super-resolution reconstruction method and device, equipment and a medium, and relates to the field of artificial intelligence, and the method comprises the steps: obtaining a down-sampling image obtained by carrying out the down-sampling of an original resolution image, and carrying out the feature extraction of the down-sampling image, so as to obtain an initial feature map; carrying out two times of random sampling on the initial feature map according to a preset sampling ratio to respectively obtain a first feature map and a second feature map, and constructing a contrast loss function based on the first feature map and the second feature map; processing the initial feature map by using a preset up-sampling method to obtain a super-resolution image, and constructing an L1 loss function based on the original resolution image and the super-resolution image; and constructing a total loss function based on the comparison loss function and the L1 loss function, and training the original super-resolution model by using the total loss function. According to the method, the comparison loss function is constructed and combined with the L1 loss function to train the original super-resolution model, so that the performance of the model is improved.

Description

technical field [0001] The present invention relates to artificial intelligence technology, in particular to a model training method, super-resolution reconstruction method, device, equipment and medium. Background technique [0002] Super Resolution (SR) is the process of restoring a high resolution (High Resolution, HR) image from a given low resolution (Low Resolution, LR) image, which is a classic application of computer vision. Through software or hardware methods, corresponding high-resolution images are reconstructed from observed low-resolution images, in the fields of monitoring equipment, satellite image remote sensing, digital high-definition, microscopic imaging, video coding communication, video restoration, and medical imaging. All have important application value. At present, when using a super-resolution model to reconstruct an image to obtain a corresponding super-resolution image, there are still problems of low image quality and unclear image quality. ...

AI Technical Summary

Problems solved by technology

At present, when using the super-resolution model to reconstruct the image to obtain the corresponding super-resolution image, there are still problems of low image quality and unclear

Images