An image super-resolution reconstruction method based on wavelet coefficients learning

A technology of super-resolution reconstruction and wavelet coefficients, applied in the field of image super-resolution based on wavelet coefficient learning, can solve problems such as a large number of calculations, long training time, lack of detailed information, etc., to achieve good results, reduce computational burden, increase The effect of sparsity

Active Publication Date: 2019-04-16
KUNMING UNIV OF SCI & TECH
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

2) For gradient disappearance/explosion, it is difficult to converge
[0005] However, the above CNN-based methods also have some shortcomings: 1) It is easy to produce over-smoothed (Over-Smoothed) results, lacking some detailed information; 2) Often use fixed ups...

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
  • An image super-resolution reconstruction method based on wavelet coefficients learning
  • An image super-resolution reconstruction method based on wavelet coefficients learning
  • An image super-resolution reconstruction method based on wavelet coefficients learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] Embodiment 1: Several different pictures are processed according to the above method, and the specific steps are as follows:

[0025] (1) Select the training set commonly used in the super-resolution method, the training set in the present embodiment uses 800 pieces of 2k resolution images in DIV2K and 2650 pieces of 2k resolution images in Flickr2K, to the high-resolution images in the training set Perform bicubic interpolation and downsampling to obtain the corresponding low-resolution image. When the magnification factor is 4, cut the image into 48×48 low-resolution image blocks Y LR , corresponding to the intercepted high-resolution image block Y of size 192×192 HR , and randomly intercept an image block of a certain size to generate a high-resolution image block Y HRand its corresponding low-resolution image patch Y LR , and randomly flip and rotate it by 90 degrees, so as to increase the number of different image forms while keeping the total number of images un...

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 discloses an image super-resolution reconstruction method based on wavelet coefficient learning, belonging to the field of image super-resolution. the method includes selecting that image train set and the test set; obtaining The wavelet coefficients of LR image and HR image by two-dimensional stationary wavelet transform of low-resolution image and two-dimensional wavelet packet transform of high-resolution image respectively. 3, constructing a depth neural network; 4, extracting that depth network feature of the wavelet coefficients of the LR image by use the depth neural network, and obtaining the wavelet residual coefficients of the HR image; Step 5, restoring the obtained wavelet residual coefficients of the HR image to the wavelet coefficients of the HR, and carrying out the two-dimensional wavelet packet inverse transform to obtain the final high-resolution image. Compared with the prior art, the invention can perform super-resolution reconstruction on an image ina very short time by training a depth super-resolution model by using a large number of external training sets, and the reconstruction result is obviously superior to most algorithms.

Description

technical field [0001] The invention belongs to the field of image super-resolution, in particular to an image super-resolution method based on wavelet coefficient learning. Background technique [0002] Single image super-resolution reconstruction technology (Single Image Super-Resolution, SISR) refers to a given single low-resolution image, through a specific algorithm to restore the details of the image lost due to downsampling, so as to obtain more detailed information , The process of high pixel density images with more delicate picture quality. Due to the ability to recover finer details with limited information, this technology has been widely used in various application scenarios, such as high-definition television broadcasting, video surveillance, and satellite imaging. Since the downsampling process of a high-resolution image under different conditions will obtain a low-resolution image with different details, the reconstruction process from a low-resolution image...

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
IPC IPC(8): G06T3/40
CPCG06T3/4053G06T3/4084
Inventor 李孟宸黄欢
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap