Image super-resolution method based on improved generative adversarial network

A super-resolution and high-resolution image technology, applied in the field of image super-resolution, can solve problems such as unpleasant artifacts, unreal textures of pictures, etc., and achieve the effect of solving artifacts

Pending Publication Date: 2022-05-10
CHONGQING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But there are also some problems, such as the reconstructed picture will have some unreal textures and unpleasant artifacts, etc.

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 super-resolution method based on improved generative adversarial network
  • Image super-resolution method based on improved generative adversarial network
  • Image super-resolution method based on improved generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] Embodiments of the present invention are described below through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation modes, and various modifications or changes can be made to the details in this specification based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the diagrams provided in the following embodiments are only schematically illustrating the basic concept of the present invention, and the following embodiments and the features in the embodiments can be combined with each other in the case of no conflict.

[0052]Wherein, the accompanying drawings are for illustrative purposes only, and represent only schematic diagrams, rather than physical drawings, and should ...

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 relates to an image super-resolution method based on an improved generative adversarial network, and belongs to the field of image processing. Obtaining a high-resolution image data set, and dividing the data set into a training set and a test set; performing bicubic downsampling on the high-resolution image training set to obtain a low-resolution image data set; an RFB module and a residual block are used in a generator module of the ESRGAN, and a U-net discriminator is used for replacing a relative discriminator in a discriminator module of the ESRGAN; lPIPS perception loss and L1 loss are introduced into the loss function to improve a generation loss function of the GAN network. Inputting the low-resolution image in the training set into a generator G for training, and outputting a reconstructed super-resolution image; and inputting the output result of the generator G and the original high-resolution image into a U-net discriminator DU. According to the method, the quality of the super-resolution image can be effectively improved, and artifacts and unreal details in the image are reduced.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to an image super-resolution method based on an improved generation confrontation network. Background technique [0002] In the field of image processing, image super-resolution has always been a topic worthy of research. In the Internet age, image super-resolution has applications in many ways. Image super-resolution technology can use software to improve the resolution of images, and can magnify images by a large factor while maintaining the clarity of images. These advantages have received extensive attention in Internet communication and storage devices. Image super-resolution technology can well meet the user's requirements for image details, so that humans can obtain a better visual and interactive experience. [0003] However, existing image super-resolution algorithms have more or less problems. There are currently three types of research methods, which are interpolation-ba...

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): G06T3/40G06T5/50G06N3/04G06N3/08
CPCG06T3/4053G06T5/50G06N3/08G06T2207/20081G06T2207/20084G06T2207/20021G06N3/045
Inventor 赵军王银
Owner CHONGQING UNIV OF POSTS & TELECOMM
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