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

Multi-level image compression method using Transform

An image compression, multi-level technology, applied in the direction of image communication, digital video signal modification, electrical components, etc., can solve the problem of discarding, and achieve the effect of small hardware requirements, excellent global information learning ability, and excellent image compression effect

Pending Publication Date: 2021-11-26
BEIJING JIAOTONG UNIV
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The aforementioned works discarded the decoder component when referring to the Transformer

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
  • Multi-level image compression method using Transform
  • Multi-level image compression method using Transform
  • Multi-level image compression method using Transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0043] The present invention proposes an end-to-end multi-level image compression method implemented using Transformer, the overall frame diagram is as follows figure 1 shown.

[0044] The input image data x is first calculated by the encoding end of the compression framework to obtain the potential feature y of the image, and then the encoding part of the super-prior module calculates y to extract side information z, z is first quantized and then passed through the decoding part of the super-prior module reconstructed features It is spliced ​​with the masked y and input to the context prediction module to predict the probability distribution of y. The probability model adopts a mixed Gaussian distribution model composed of three sub-Gaussian distributions. During the training process, y is directly quan...

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 a multi-level image compression method using Transform, which is characterized in that a multi-level image compression frame is mainly composed of a Transform module and is supplemented by a convolutional layer neural network, the Transform module comprises multiple layers of encoder components and decoder components, the encoder components are adopted at an encoding end, and the decoder components are adopted at a decoding end; the decoder has a cross attention mechanism, and the cross attention mechanism carries out joint calculation on the self attention features input by the decoder and the self attention features of the encoder, and makes full use of the features learned by the encoding end of the compression frame encoder. According to the method, a decoder component and a cross attention mechanism thereof in Transform are reserved, the method is applied to a decoding end to realize full utilization of features learned by a coding end, and a better effect is achieved. And the requirement of the framework on hardware is smaller.

Description

technical field [0001] The present application relates to the field of computer technology image processing, in particular to a multi-level image compression method using Transformer. Background technique [0002] With the rapid development of the Internet and digital media, and the advent of the era of big data, a large amount of image data is generated, stored and transmitted on the Internet every day, and these data will take up a lot of space and bandwidth. In order to achieve more efficient storage and transmission of image data, image compression algorithms came into being. Image compression aims to reduce the amount of data required to represent digital images by removing redundant information in image data, so as to achieve efficient compression of image data, which is also one of the common basic research issues in the field of image processing. [0003] In an earlier period, some classic traditional image compression algorithms were studied, such as discrete cosin...

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): H04N19/103H04N19/20H04N19/30H04N19/42
CPCH04N19/30H04N19/42H04N19/20H04N19/103
Inventor 刘美琴梁甲名林春雨白慧慧赵耀
Owner BEIJING JIAOTONG 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