Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image reconstruction method based on blind super-resolution network

An image reconstruction and resolution technology, which is applied in the directions of graphics and image conversion, image data processing, neural learning methods, etc., can solve the problems of blurred texture and structural distortion of the reconstructed image, and achieve the effect of accurate texture and accurate estimation

Pending Publication Date: 2022-05-13
XIDIAN UNIV
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies in the prior art above, and propose an image reconstruction method based on a blind super-resolution network, aiming to solve the inaccurate estimation of the blur kernel in the prior art under the premise of ensuring the image resolution Technical issues leading to blurred textures and structural distortions in reconstructed images

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image reconstruction method based on blind super-resolution network
  • Image reconstruction method based on blind super-resolution network
  • Image reconstruction method based on blind super-resolution network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Below in conjunction with the accompanying drawings and specific embodiments, the present invention is described in further detail:

[0028] refer to figure 1 , the present invention comprises the steps:

[0029] Step 1) Obtain the training sample set R 1 and the test sample set E 1 :

[0030] Step 1a) Obtain K RGB images from the DIV2K and Flickr2K datasets, where K≥2000. In this embodiment, K=3450;

[0031] Step 1b) In order to simulate the real-world downsampling process and facilitate the comparison between different experiments, each RGB image is subjected to Gaussian blurring with different parameters at random, and each Gaussian blurred RGB image is subjected to 1 / 4 downsampling, The implementation steps are: set the Gaussian blur kernel size to 21, σ is randomly selected in the [0.2, 4.0] interval, perform template convolution on each RGB image, and perform 1 / 4 bicubic on each Gaussian blurred RGB image. downsampling;

[0032]Step 1c) Crop each RGB image ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an image reconstruction method based on a blind super-resolution network. The method comprises the following implementation steps: (1) obtaining a training sample set and a test sample set; (2) constructing an image reconstruction model O based on the blind super-resolution network; (3) carrying out iterative training on the blind super-resolution image reconstruction network model O; and (4) obtaining an image reconstruction result. According to the blind super-resolution image reconstruction model constructed by the invention, blurring kernel estimation and blurring kernel correction can be adaptively carried out according to different degraded images, so that the estimated blurring kernel is more accurate, and the technical problems of texture blurring and structure distortion of the reconstructed image caused by inaccurate blurring kernel estimation in the prior art are solved; and on the premise of ensuring the resolution of the reconstructed image, the quality of the reconstructed image is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image reconstruction method, in particular to an RGB image reconstruction method based on a blind super-resolution network, which can be used in the fields of video surveillance, remote sensing imaging and the like. Background technique [0002] During the imaging process, due to the influence of various factors of the imaging system, the obtained image may not be a perfect image of the real scene. The process of degrading image quality during image formation, dissemination and preservation is called image degradation. Image reconstruction is the process of reconstructing degraded images to maximize the restoration of the original appearance of the scene. Image reconstruction can only try to make the image as close to its original image as possible, but due to factors such as noise interference, it is difficult to restore it accurately. However, due to the limitation ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T3/40G06N3/04G06N3/08
CPCG06T3/4053G06N3/08G06N3/048G06N3/045
Inventor 路文胡健孙晓鹏张立泽高新波何立火
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com