Structural tensor total variation-based image and video super-resolution method

Abstract

The invention discloses a structural tensor total variation-based image and video super-resolution method. The method includes the following steps that: an image degradation model is established, wherein the image degradation model includes a blurring part and a downsampling part and is expressed as an expression described in the descriptions of the invention, wherein x represents an original high-resolution image, B represents a blurring kernel, a symbol, described in the descriptions, represents a convolution process, D represents downsampling of a corresponding multiple, and y represents a generated low-resolution image; a super-resolution model is established, wherein the super-resolution model includes an image interpolation part and a de-blurring part and is expressed as an expression described in the descriptions of the invention, wherein x<^> represents a restored high-resolution image, B represents a blurring kernel, a symbol, described in the descriptions, represents a deconvolution process, D<-1> represents an interpolating process of a corresponding multiple, and y represents a low-resolution image; and a structural tensor total variation regularization constraint-based super-resolution model is constructed and is expressed as an expression described in the descriptions of the invention, wherein Mu is a parameter that can be adjusted, so that the strength of the constraint of a regularization term can be realized. With the structural tensor total variation-based image and video super-resolution method adopted, over-smoothing and an edge step effect caused by a condition that a total variation model directly constrains an image, are avoided, and a processing effect obtained by using the method of the invention more accords with the subjective feeling of eyes.

Description

technical field [0001] The invention belongs to the technical field of video image processing, in particular to an image video super-resolution method based on structural tensor total variation. Background technique [0002] Image super-resolution refers to a class of methods that use a computer to enlarge a low-resolution image into a high-resolution image, and estimate the image information that needs to be supplemented during the enlargement process. [0003] Video super-resolution is divided into two categories. One is to reconstruct a key frame from a video by using the information of multiple frames, which has many applications in monitoring. The other type refers to amplifying each frame of the video to generate a high-resolution video, which is mainly used in the field of video broadcasting. [0004] The use of digital image generating equipment (digital cameras, digital video cameras, etc.) has become more and more popular, which also makes digital images more and ...

AI Technical Summary

Problems solved by technology

However, the problem with the TV model is that the final solution may be over-smoothed, that is, details and textures will be smoothed out except for smooth areas and strong edge areas.

Images