Image super-resolution reconstruction method and device, equipment and storage medium

Abstract

The invention discloses an image super-resolution reconstruction method and device, equipment and a storage medium, and the method comprises the steps: obtaining a training set composed of a high-resolution image HR and a low-resolution image LR obtained through the down-sampling of the high-resolution image HR; constructing a generative adversarial network model comprising a generator network and a discriminator network, inputting the training set into the generative adversarial network model, and training the generative adversarial network model by using a loss function which comprises a loss function of the generator network, wherein the loss function of the generator network comprises a content loss function and an adversarial loss function, the content loss function comprises a VGG network loss function, an illumination loss function and a structural similarity loss function, and the expression of the loss function of the generator network is shown in the specification. According to the scheme, the generative adversarial network model is more sensitive to the illumination intensity, and the visual quality of the generated image is better.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to an image super-resolution reconstruction method, device, equipment and storage medium. Background technique [0002] Single Image Super-Resolution (SISR) aims to restore super-resolution images (SR) from low-resolution images (LR) to obtain near-real high-resolution images (HR). This has direct applications in many fields such as medical imaging, satellite imaging, face recognition and video surveillance, etc. At present, people have higher and higher requirements for images, especially in terms of clarity. Improving the image definition purely from the hardware aspect is not only costly but also reaches a certain technical bottleneck. At the same time, low-resolution images will be produced in the case of image storage and insufficient light at night. Improving the image resolution from the software aspect overcomes the above-mentioned deficiencies to a ...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present application provide an image super-resolution reconstruction method, device, device, and storage medium, which can make the generated confrontation network model more sensitive to light intensity, solve the problem of single image super-resolution under low light, and can make the generated Image visual quality is better and more natural

Images