Entropy coding/decoding method and device

An entropy encoding and encoding technology, applied in the field of entropy encoding/decoding methods and devices, can solve problems such as video size becoming a problem

Active Publication Date: 2022-04-12
HUAWEI TECH CO LTD
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The size of the video can also be an issue when storing the video on a storage device due to potentially limited memory resources

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
  • Entropy coding/decoding method and device
  • Entropy coding/decoding method and device
  • Entropy coding/decoding method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0345] Figure 13An exemplary flow chart of the entropy encoding method of the present application, such as Figure 13 As shown, x represents the original value of the image block. In the video encoder, x is encoded by an encoder based on the hybrid coding framework to obtain the first coded stream corresponding to the basic layer information, and the first coded stream is then decoded by a decoder based on the hybrid decoding framework to obtain the reconstruction of the image block value xc. The video encoder inputs the reconstruction value xc of the image block into the neural network to obtain K sets of probability values. optional, such as Figure 14 As shown, the video encoder can first input the reconstruction value xc of the image block into Encoder2 for feature extraction before inputting the reconstruction value xc of the image block into the neural network, and then input the feature value corresponding to the reconstruction value xc of the image block into the n...

Embodiment 2

[0349] Figure 15 An exemplary flow chart of the entropy encoding method of the present application, such as Figure 15 As shown, x represents the original value of the image block. The difference from the first implementation is that the video encoder and decoder input the residual value Δx of the image block into the neural network, that is, in this embodiment, K groups of probability values ​​are obtained based on the residual value Δx of the image block.

Embodiment 3

[0351] Figure 16 An exemplary flow chart of the entropy encoding method of the present application, such as Figure 16 As shown, x represents the original value of the image block. The difference from Implementation 1 is that the video encoder and decoder input both the residual value Δx of the image block and the reconstruction value xc of the image block into the neural network, that is, in this embodiment, it is based on the residual value Δx of the image block and the reconstruction value xc of the image block The reconstructed value xc obtains K sets of probability values.

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 entropy coding / decoding method and device. Relates to the technical field of video or image compression based on artificial intelligence (AI), in particular to the technical field of video compression based on a neural network. The method comprises the steps that basic layer information of an image block to be coded is obtained, the basic layer information corresponds to M pixel points in the image block, and M is a positive integer; k elements corresponding to enhancement layer information of the image block are obtained, the enhancement layer information corresponds to N pixel points in the image block, both K and N are positive integers, and N is larger than or equal to M; the basic layer information is input into a neural network to obtain K groups of probability values, the K groups of probability values correspond to the K elements, and any group of probability values is used for representing the probability of a plurality of candidate values of the corresponding element; and performing entropy coding on the K elements according to the K groups of probability values. According to the invention, the entropy coding / decoding efficiency can be improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of video or image compression based on artificial intelligence (AI), and in particular, to an entropy encoding / decoding method and device. Background technique [0002] Video coding (video encoding and decoding) is widely used in digital video applications such as broadcast digital TV, video transmission over the Internet and mobile networks, real-time session applications such as video chat and video conferencing, DVD and Blu-ray discs, video content acquisition and editing systems and security applications for camcorders. [0003] Large amounts of video data need to be described even in the case of short movies, which can cause difficulties when the data is to be sent or otherwise transmitted over a network with limited bandwidth capacity. Therefore, video data is usually compressed before being transmitted over modern telecommunications networks. Since memory resources may be limit...

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): H04N19/91H04N19/88H04N19/176
CPCH04N19/91G06N3/0464G06N3/048G06N3/0455G06N3/047G06N3/088G06N3/044G06N3/084G06N3/0475G06N3/094H04N19/30H04N19/13H04N19/132H04N19/172H04N19/176H04N19/42H04N19/50H04N19/70
Inventor毛珏杨海涛马祥
OwnerHUAWEI TECH CO LTD