Methods and systems for video coding

Patent metadata

Field	Value
Publication number	US-12439055-B2
Application number	US-202318171304-A
Country	US
Kind code	B2
Filing date	Feb 17, 2023
Priority date	Feb 22, 2021
Publication date	Oct 7, 2025
Grant date	Oct 7, 2025

Abstract

The present disclosure may relate to a system and a method for video coding. The method may include determining at least one classification mode of a first component of a first pixel for a block in an image frame based on at least one pixel value of at least one second component of at least one second pixel that surrounds the first pixel. The method may also include generating a target classification result by classifying the first component based on at least a portion of the at least one classification mode. The method may also include compensating the first component based on an optimal compensation value of the target classification result.

First claim

What is claimed is:

1. A method for video coding, comprising:
determining at least one classification mode of a first component of a first pixel for a block in an image frame based on at least one pixel value of at least one second component of at least one second pixel, wherein the at least one second component of the at least one second pixel has a distance with the first component of the first pixel and the distance does not exceed a range, the first component includes a chrominance component, and each of the at least one second component includes a luminance component, and the determining the at least one classification mode includes:
designating a pixel value of one of the at least one second component or one of at least one statistical value of the at least one first component as a value of one of the at least one classification mode;

generating a target classification result by classifying the first component based on at least a portion of the at least one classification mode; and
compensating the first component based on an optimal compensation value of the target classification result.

2. The method of claim 1 , wherein the determining at least one classification mode of a first component of a first pixel for a block in an image based on at least one pixel value of at least one second component of at least one second that surrounds the first pixel includes:
determining at least one statistical value of the at least one pixel value of the at least one second component of the at least one second pixel that surrounds the first pixel, wherein each of the at least one statistical value refers to a value determined by performing a statistical analysis on the at least one pixel value of the at least one second component.

3. The method of claim 2 , wherein the at least one statistical value includes a maximum value, a minimum value, a median value, or an average value of the at least one pixel value of the at least one second component.

4. The method of claim 1 , further comprising:
determining whether one of the at least one second component corresponding to one of the at least one classification mode is outside a boundary associated with the block;
in response to a determination result that the one of the at least one second component corresponding to the classification mode is outside the boundary,
obtaining an updated classification mode based on the classification mode; and
classifying the first component based on the updated classification mode.

5. The method of claim 4 , wherein the boundary includes one or more of a boundary of the block, a boundary of a slice in the block, or a boundary of a patch in the block.

6. The method of claim 4 , wherein the updated classification mode is obtained by assigning a value to the classification mode.

7. The method of claim 6 , wherein the value is determined based on a pixel value of a third component of a third pixel adjacent to the one of the at least one second pixel.

8. The method of claim 1 , further comprising:
performing loop filtering on the compensated first component based on at least one filter.

9. A system for video coding, comprising:
at least one storage medium storing a set of instructions;
at least one processor in communication with the at least one storage medium, when executing the stored set of instructions, the at least one processor causes the system to:
determine at least one classification mode of a first component of a first pixel for a block in an image frame based on at least one pixel value of at least one second component of at least one second pixel, wherein the at least one second component of the at least one second pixel has a distance with the first component of the first pixel and the distance does not exceed a range, the first component includes a chrominance component, and each of the at least one second component includes a luminance component, and to determine the at least one classification mode, the at least one processor causes the system further to:
designate a pixel value of one of the at least one second component or one of at least one statistical value of the at least one first component as a value of one of the at least one classification mode;
generate a target classification result by classifying the first component based on at least a portion of the at least one classification mode; and
compensate the first component based on an optimal compensation value of the target classification result.

10. The system of claim 9 , wherein to determine at least one classification mode of a first component of a first pixel for a block in an image based on at least one pixel value of at least one second component of at least one second that surrounds the first pixel, the at least one processor causes the system to:
determine at least one statistical value of the at least one pixel value of the at least one second component of the at least one second pixel that surrounds the first pixel, wherein each of the at least one statistical value refers to a value determined by performing a statistical analysis on the at least one pixel value of the at least one second component.

11. The system of claim 10 , wherein the at least one statistical value includes a maximum value, a minimum value, a median value, or an average value of the at least one pixel value of the at least one second component.

12. The system of claim 9 , wherein the at least one processor causes the system further to:
determine whether one of the at least one second component corresponding to one of the at least one classification mode is outside a boundary associated with the block;
in response to a determination result that the one of the at least one second component corresponding to the classification mode is outside the boundary,
obtain an updated classification mode based on the classification mode; and
classify the first component based on the updated classification mode.

13. The system of claim 12 , wherein the boundary includes one or more of a boundary of the block, a boundary of a slice in the block, or a boundary of a patch in the block.

14. The system of claim 12 , wherein the updated classification mode is obtained by assigning a value to the classification mode.

15. The system of claim 14 , wherein the value is determined based on a pixel value of a third component of a third pixel adjacent to the one of the at least one second pixel.

16. The method of claim 1 , wherein generating a target classification result by classifying the first component based on at least a portion of the at least one classification mode includes:
classifying the first component according to each of the at least one classification mode to obtain at least one classification result;
determining a cost for each of the at least one classification result determined based on the at least one classification mode;
determining one of the at least one classification mode with a minimum cost as a target classification mode;
classifying the first component using the target classification mode to obtain the target classification result, the target classification result including multiple types of the first component.

17. The method of claim 1 , wherein compensating the first component based on an optimal compensation value of the target classification result includes:
determining the optimal compensation value for the target classification result based on a rate distortion optimization (RDO) process;
compensating the first component based on the optimal compensation value of the target classification result, the compensating t

Assignees

• Zhejiang Dahua Technology Co

Inventors

• Zhang Xue
• Jiang Dong
• Nian Chunmei
• Lin Jucai
• Yin Jun

Classifications

• H04N19/82

  involving filtering within a prediction loop · CPC title

• H04N19/186

  the unit being a colour or a chrominance component · CPC title

• H04N19/182

  the unit being a pixel · CPC title

• H04N19/117

  Filters, e.g. for pre-processing or post-processing (sub-band filter banks H04N19/635) · CPC title

• H04N19/136

  Incoming video signal characteristics or properties · CPC title