IP Library Granted Patent US 12701250
Granted Patent B2
US 12701250 · App. 18/381,415 · Granted Aug 4, 2026

Modified intra prediction fusion

Inventors: Xin Zhao (San Jose, CA); Guichun Li (San Jose, CA); Lien-Fei Chen (Hsinchu, TW); Shan Liu (San Jose, CA)
Assignee: Tencent America LLC
H04N19/44H04N19/132H04N19/159H04N19/176
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12701250
App. No.
18/381,415
Granted
Aug 4, 2026
Kind
B2
Abstract

Aspects of the disclosure include methods and apparatuses for video coding. One of the apparatuses includes processing circuitry that receives a current block in a bitstream. The current block is predicted with intra prediction fusion comprising multiple candidate intra prediction modes. The processing circuitry determines a respective candidate prediction value of a sample in the current block for each of the multiple candidate intra prediction modes. The processing circuitry derives weights of the respective multiple candidate intra prediction modes based on intra prediction modes used to code neighboring blocks of the current block. The processing circuitry predicts, according to the derived weights, the sample in the current block by a weighted sum of the candidate prediction values associated with the multiple candidate intra prediction modes.

Claims (41)

1 . A method of video decoding, comprising:

receiving a current block in a bitstream, the current block being predicted with an intra prediction fusion comprising multiple candidate intra prediction modes;

determining a respective candidate prediction value of a sample in the current block in each of the multiple candidate intra prediction modes;

deriving weights of the candidate prediction values associated with the respective multiple candidate intra prediction modes based on intra prediction modes used to code neighboring blocks of the current block; and

predicting, according to the derived weights, the sample in the current block by a weighted sum of the candidate prediction values associated with the multiple candidate intra prediction modes, wherein

the weight of one of the multiple candidate intra prediction modes is derived based on (i) a first frequency of occurrences that the one of the multiple candidate intra prediction modes is applied to code left neighboring blocks in the neighboring blocks and (ii) a second frequency of occurrences that the one of the multiple candidate intra prediction modes is applied to code top neighboring blocks in the neighboring blocks.

2 . The method of claim 1 , wherein the deriving comprises:

determining frequencies of occurrences that the multiple candidate intra prediction modes are applied to code the neighboring blocks, the frequencies of occurrences including the first frequency of occurrences.

3 . The method of claim 1 , wherein the deriving comprises:

deriving a horizontal weight of the one of the multiple candidate intra prediction modes based on the first frequency of occurrences;

deriving a vertical weight of the one of the multiple candidate intra prediction modes based on the second frequency of occurrences; and

deriving the weight of the one of the multiple candidate intra prediction modes based on the derived horizontal weight and the derived vertical weight.

4 . The method of claim 3 , wherein the deriving the horizontal weight comprises:

determining the first frequency of occurrences that the one of the multiple candidate intra prediction modes is applied to code the left neighboring blocks in the neighboring blocks.

5 . The method of claim 3 , wherein the deriving the vertical weight comprises:

determining the second frequency of occurrences that the one of the multiple candidate intra prediction modes is applied to code the top neighboring blocks in the neighboring blocks.

6 . The method of claim 3 , wherein the deriving the weight comprises:

deriving a first weight for the horizontal weight and a second weight for the vertical weight based on a relative coordinate of the sample with respect to a top-left coordinate in the current block; and

deriving the weight of the one of the multiple candidate intra prediction modes based on a weighted sum of the derived horizontal weight and the derived vertical weight using the first weight and the second weight, respectively.

7 . The method of claim 3 , wherein the deriving the weight comprises:

deriving the weight of the one of the multiple candidate intra prediction modes based on a bilinear interpolation of the horizontal weight, the vertical weight, a default horizontal weight and a default vertical weight.

8 . The method of claim 1 , wherein the multiple candidate intra prediction modes comprise one or more of a DC mode, a planar mode, an intra directional prediction mode, a decoder-side intra mode derivation (DIMD) mode, a template based intra mode derivation (TIMD) mode, a cross-component linear model (CCLM), a convolutional cross-component model (CCCM), and a multi-model linear mode (MMLM).

9 . A method of video decoding, comprising:

receiving a current block in a bitstream including coding information indicating that the current block is predicted with an intra prediction fusion comprising multiple candidate intra prediction modes;

determining a respective candidate prediction value of a sample in the current block for each of the multiple candidate intra prediction modes;

calculating template matching costs between a current template including neighboring reconstructed samples of the current block and respective reference templates of the current template that are indicated by the multiple candidate intra prediction modes, the neighboring reconstructed samples including reconstructed samples within at least one line of the current block;

deriving weights of the respective multiple candidate intra prediction modes based on the respective template matching costs; and

predicting, according to the derived weights, the sample in the current block by a weighted sum of the candidate prediction values associated with the multiple candidate intra prediction modes.

10 . An apparatus for video encoding, comprising:

processing circuitry configured to:

determine a respective candidate prediction value of a sample in a current block for each of multiple candidate intra prediction modes, the current block being predicted with intra prediction fusion comprising the multiple candidate intra prediction modes;

derive weights of the candidate prediction values associated with the respective multiple candidate intra prediction modes based on intra prediction modes used to code neighboring blocks of the current block; and

predict, according to the derived weights, the sample in the current block by a weighted sum of the candidate prediction values associated with the multiple candidate intra prediction modes, wherein

the weight of one of the multiple candidate intra prediction modes is derived based on (i) a first frequency of occurrences that the one of the multiple candidate intra prediction modes is applied to code left neighboring blocks in the neighboring blocks and (ii) a second frequency of occurrences that the one of the multiple candidate intra prediction modes is applied to code top neighboring blocks in the neighboring blocks.

11 . The apparatus of claim 10 , wherein the processing circuitry is configured to:

determine frequencies of occurrences that the multiple candidate intra prediction modes are applied to code the neighboring blocks, the frequencies of occurrences including the first frequency of occurrences.

12 . The apparatus of claim 10 , wherein the processing circuitry is configured to:

derive a horizontal weight of the one of the multiple candidate intra prediction modes based on the first frequency of occurrences;

derive a vertical weight of the one of the multiple candidate intra prediction modes based on the second frequency of occurrences; and

derive the weight of the one of the multiple candidate intra prediction modes based on the derived horizontal weight and the derived vertical weight.

13 . The apparatus of claim 10 , wherein the multiple candidate intra prediction modes comprise one or more of a DC mode, a planar mode, an intra directional prediction mode, a decoder-side intra mode derivation (DIMD) mode, a template based intra mode derivation (TIMD) mode, a cross-component linear model (CCLM), a convolutional cross-component model (CCCM), and a multi-model linear mode (MMLM).