Unlock instant, AI-driven research and patent intelligence for your innovation.

An Image Compression Quality Enhancement Method Based on Knowledge Distillation

An image compression and quality enhancement technology, applied in the field of image compression quality enhancement based on knowledge distillation, can solve problems such as difficult application and high decoding complexity

Active Publication Date: 2022-07-15
UNIV OF SCI & TECH OF CHINA
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the decoder of end-to-end deep learning image coding is also based on deep neural network, and the decoding complexity is much higher than that of hybrid frame image coding, so it is currently difficult to apply to real-world scenarios

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 Compression Quality Enhancement Method Based on Knowledge Distillation
  • An Image Compression Quality Enhancement Method Based on Knowledge Distillation
  • An Image Compression Quality Enhancement Method Based on Knowledge Distillation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

[0015] The embodiment of the present invention provides an image compression quality enhancement method based on knowledge distillation, such as figure 1 As shown, it mainly includes the following steps:

[0016] Step 1. Use the original optimization objective A and the desired optimization objective B of the target encoder to optimize the auxiliary encoder respectively, and obtain two optimized auxiliary encoders.

[0017] In the embodiment of the prese...

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 compression quality enhancement method based on knowledge distillation. using the optimized two auxiliary encoders to encode the same image respectively to obtain two bit rate allocation results of the image; use the two bit rate allocation results to adjust the coding parameters of the target encoder; use the coding parameters to adjust The latter target encoder encodes the image. This method can effectively optimize the non-mean-square error index without modifying the decoder.

Description

technical field [0001] The invention relates to the technical field of image compression, in particular to an image compression quality enhancement method based on knowledge distillation. Background technique [0002] At present, the most advanced hybrid frame image coding method in terms of compression efficiency is BPG (Better Portable Graphics), which is also transformed from intra-frame coding based on the video coding standard H.265. Compared with H.265, the new-generation video coding standard H.266 with more advanced intra-frame coding saves more than 30% of the bit rate under the same quality. After decades of continuous development, while the compression efficiency of hybrid frame image coding continues to increase, the system complexity has become higher and higher, and the performance of a single technology has become smaller and smaller, and has tended to be saturated to a certain extent. All these methods, mainly, use the mean squared error as the optimization ...

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 Patents(China)
IPC IPC(8): H04N19/146H04N19/172H04N19/42H04N19/70H04N19/91H04N19/96
CPCH04N19/146H04N19/172H04N19/42H04N19/70H04N19/91H04N19/96
Inventor 刘东杨闰宇吴枫
Owner UNIV OF SCI & TECH OF CHINA