Image processing method and device, electronic equipment and storage medium

Abstract

The invention relates to the field of image processing, in particular to an image processing method and device, electronic equipment and a storage medium. The image processing method comprises the steps: obtaining a to-be-processed original image and a reference image corresponding to the original image, wherein the resolution of the reference image is greater than that of the original image; performing feature extraction on the original image to obtain a first feature set; performing feature extraction on the reference image to obtain a second feature set; performing feature alignment according to the first feature set and the second feature set to obtain a plurality of alignment feature data with a plurality of different image scales; and performing feature fusion on the plurality of alignment feature data and the original image to obtain a processed target image. Characteristic alignment is carried out layer by layer through pyramid cascading according to characteristic data of different scales, so reference image characteristics are effectively matched to corresponding positions of an original image, influences caused by different shooting angles or shooting time are reduced oreliminated, and the reference image characteristics are more effectively combined in the image super-division process.

Description

technical field [0001] The present disclosure relates to the field of image processing, and in particular to an image processing method, device, electronic equipment, and storage medium. Background technique [0002] Image super-resolution reconstruction refers to the process of reconstructing low-resolution original images into higher-resolution images, so that more image information can be obtained from high-resolution images. Image super-resolution research can be mainly divided into single-scene reconstruction (SISR) and multi-scene reconstruction (MISR). Multi-scene reconstruction uses multiple low-resolution images (LR) of the same scene, and uses complementary information between them to High-resolution images (HR) are reconstructed, but in practical applications, multiple LR images are often not available, so limited LR information needs to be used to reconstruct HR images, that is, single-view reconstruction. [0003] In related technologies, in the single-scene su...

AI Technical Summary

Problems solved by technology

Image super-resolution research can be mainly divided into single-scene reconstruction (SISR) and multi-scene reconstruction (MISR). Multi-scene reconstruction uses multiple low-resolution images (LR) of the same scene, and uses complementary information between them to High-resolution images (HR) are reconstructed, but in practical applications, it is often impossible to obtain multiple LR images, so it is n

Images