# US 2022/0277491 A1 · Method and device for machine learning-based image compression using global context

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0277491 A1
- Document ID: US20220277491A1
- Status: Published application
- Kind: A1
- Application number: 17/615,519
- Filed: 2020-05-29
- Published: 2022-09-01
- Earliest claimed: 2019-05-31
- Assignees: Electronics and Telecommunications Research Institute
- Applicants: Electronics and Telecommunications Research Institute
- Inventors: Joo-Young LEE; Seung-Hyun CHO; Hyunsuk KO; Hyoung-Jin KWON; Youn-Hee KIM; Jong-Ho KIM; Se-Yoon JEONG; Hui-Yong KIM; Jin-Soo CHOI
- Web page: https://patentgrep.com/patent/US20220277491A1

## CPC

- G06T 9/002: {using neural networks}
- H04N 19/13: Adaptive entropy coding, e.g. adaptive variable length coding [AVLC] or context adaptive binary arithmetic coding [CABAC]
- G06N 20/00: Machine learning
- G06T 3/4023: based on decimating pixels or lines of pixels; based on inserting pixels or lines of pixels
- G06T 3/4046: using neural networks
- H04N 1/41: Bandwidth or redundancy reduction (by scanning H04N1/17 {; methods or arrangements for coding, decoding, compressing or decompressing digital video signals H04N19/00})
- H04N 19/136: Incoming video signal characteristics or properties
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Disclosed herein are a method and apparatus for image compression based on machine learning using a global context. The disclosed image compression network employs an existing image quality enhancement network for an end-to-end joint learning scheme. The image compression network may jointly optimize image compression enhancement and quality enhancement. The image compression networks and image quality enhancement networks may be easily combined within a unified architecture which minimizes total loss, and may be easily jointly optimized.

## Claims

### Claim 1

An encoding method, comprising:
generating a bitstream by performing entropy encoding that uses an entropy model on an input image; and
transmitting or storing the bitstream.

### Claim 2 (depends on 1)

The encoding method of claim 1, wherein:
the entropy model is a context-adaptive entropy model, and
the context-adaptive entropy model exploits three different types of contexts.

### Claim 3 (depends on 2)

The encoding method of claim 2, wherein the contexts are used to estimate parameters of a Gaussian mixture model.

### Claim 4 (depends on 3)

The encoding method of claim 3, wherein the parameters include a weight parameter, a mean parameter, and a standard deviation parameter.

### Claim 5 (depends on 1)

The encoding method of claim 1, wherein:
the entropy model is a context-adaptive entropy model, and
the context-adaptive entropy model uses a global context.

### Claim 6 (depends on 1)

The encoding method of claim 1, wherein the entropy encoding is performed by combining an image compression network with a quality enhancement network.

### Claim 7 (depends on 6)

The encoding method of claim 6, wherein the quality enhancement network is a very deep super resolution network (VDSR), a residual dense network (RDN) or a grouped residual dense Network (GRDN).

### Claim 8 (depends on 1)

The encoding method of claim 1, wherein:
horizontal padding or vertical padding is applied to the input image,
the horizontal padding is to insert one or more rows into the input image at a center of a vertical axis thereof, and
the vertical padding is to insert one or more columns into the input image at a center of a horizontal axis thereof.

### Claim 9 (depends on 8)

The encoding method of claim 8, wherein:
the horizontal padding is performed when a height of the input image is not a multiple of k,
the vertical padding is performed when a width of the input image is not a multiple of k,
k is 2n, and
n is a number of down-scaling operations performed on the input image.

### Claim 10 (depends on 1)

A storage medium storing the bitstream generated by the encoding method of claim 1.

### Claim 11

A decoding apparatus, comprising:
a communication unit for acquiring a bitstream; and
a processing unit for generating a reconstructed image by performing decoding that uses an entropy model on the bitstream.

### Claim 12

A decoding method, comprising:
acquiring a bitstream; and
generating a reconstructed image by performing decoding that uses an entropy model on the bitstream.

### Claim 13 (depends on 12)

The decoding method of claim 12, wherein:
the entropy model is a context-adaptive entropy model, and
the context-adaptive entropy model exploits three different types of contexts.

### Claim 14 (depends on 13)

The decoding method of claim 13, wherein the contexts are used to estimate parameters of a Gaussian mixture model.

### Claim 15 (depends on 14)

The decoding method of claim 14, wherein the parameters include a weight parameter, a mean parameter, and a standard deviation parameter.

### Claim 16 (depends on 12)

The decoding method of claim 12, wherein:
the entropy model is a context-adaptive entropy model, and
the context-adaptive entropy model uses a global context.

### Claim 17 (depends on 12)

The decoding method of claim 12, wherein:
the entropy decoding is performed by combining an image compression network with a quality enhancement network.

### Claim 18 (depends on 12)

The decoding method of claim 12, wherein the quality enhancement network is a very deep super resolution network (VDSR), a residual dense network (RDN) or a grouped residual dense Network (GRDN).

### Claim 19 (depends on 12)

The decoding method of claim 12, wherein:
a horizontal padding area or a vertical padding area is removed from the reconstructed image,
removal of the horizontal padding area is to remove one or more rows from the reconstructed image at a center of a vertical axis thereof, and
removal of the vertical padding area is to remove one or more columns from the reconstructed image at a center of a horizontal axis thereof.

### Claim 20 (depends on 19)

The decoding method of claim 19, wherein:
the removal of the horizontal padding area is performed when a height of an original image is not a multiple of k,
the removal of the vertical padding area is performed when a width of the original image is not a multiple of k,
k is 2n, and
n is a number of down-scaling operations performed on the original image.
