A method and device for super-resolution magnification of an image at any scale

Abstract

The present invention provides a method, system, device and storage medium for super-resolution magnification of an image at any scale. The method includes: collecting an original image data set and down-sampling images of different multiples, and respectively and different multiples of the image data set. The down-sampled images are stored in pairs as training data sets; the down-sampled images and super-resolution multiples are input into the training model to obtain the feature map of the down-sampled images, and the features are analyzed according to the super-resolution multiples. mask the image to form a new feature map; map the new feature map to a super-resolution image, calculate the loss between the super-resolution image and the original image, and update the training according to the loss model until the training is completed; and input the first resolution image to be processed and the required super-resolution multiple to the training model to obtain the super-resolution image. The present invention utilizes mask filling and image mapping to realize a super-resolution method of any scale.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, and more specifically refers to a method, system, device and storage medium for super-resolution zooming in on any scale of an image. Background technique [0002] Super Resolution (SR) is the process of recovering high resolution (HR) images from a given low resolution (LR) image, which is a classic application of computer vision. Reconstructing corresponding high-resolution images from low-resolution images (that is, increasing resolution) is important in the fields of monitoring equipment, satellite image remote sensing, digital high-definition, microscopic imaging, video coding communication, video restoration, and medical imaging. application value. [0003] One of the existing technologies, such as ESPCNN, EDSR, SRGAN, RDN and RCAN, only considers the super-resolution of certain integer scale factors (X2, X3, X4) at most. The common point of these methods is that they need to...

AI Technical Summary

Problems solved by technology

Unfortunately, this only scales the image with a fixed integer scale factor

Moreover, the model needs the image to have the same size during the training process, so the original data needs to be resized (redefined size) to grow into an image with the same width, and finally the model is only applicable to the integer scale factor, that is, a model can only be enlarged in one way multiple super-resolution

These disadvantages limit their use in real-world scenarios

Images