Image processing method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses an image processing method and device, computer equipment and a storage medium. The method comprises: obtaining a to-be-processed low-resolution image; performing feature search in a preset reference pool according to the low-resolution image to obtain a reference feature map, wherein the reference feature map is obtained by carrying out feature extractionon a high-definition image set in the reference pool; and performing feature enhancement on the low-resolution image according to the reference feature map to obtain a high-resolution image. Due to the diversification of the images in the reference pool, the reference feature map contains all possible local features, and high-frequency texture information can be provided for each low-resolution image, so that the richness of the features is ensured, and the memory burden can be reduced. Moreover, the reference feature map is searched according to the low-resolution image, and the selected reference feature map can adaptively shield or enhance various different features, so that the details of the low-resolution image are richer.

Description

technical field [0001] Embodiments of the present invention relate to the field of computer technology, in particular, an image processing method, device, computer equipment, and storage medium. Background technique [0002] Super-resolution (SR) is to process low-resolution (LR) images obtained in reality into high-resolution (HR) images, and the processing results should contain detailed textures to meet visual sensory requirements. Among them, SR, as a low-level computer vision task to improve image quality, is of great significance to a variety of high-level computer vision tasks, including image detection and classification, video transmission, monitoring and analysis, etc. [0003] At present, the super-resolution (RefSR) methods include: SRNTT, CrossNet, among them, SRNTT is the representative of RefSR, input the LR image and a HR reference image into the VGG-19 neural network at the same time to extract the feature maps of three scales, Then find a local area in the...

AI Technical Summary

Problems solved by technology

[0004] However, the above methods mainly have two drawbacks: (1) impose strict constraints on the correlation between the reference image and the LR image, such as having similar content, homogenous patterns, camera views, and relative scales, which are common in many It is impractical in practical application, which affects the image processing, and the results obtained are not ideal

(2) The above method only considers the closest feature point when performing feature search and migration, and cannot adaptively extract and enhance feature representation capabilities from multiple modes, so that obvious colors appear when the reference image mode is extremely single Bias and Artifacts

Images