Cross component prediction

Patent metadata

Field	Value
Publication number	US-12445624-B2
Application number	US-202418750267-A
Country	US
Kind code	B2
Filing date	Jun 21, 2024
Priority date	Jul 2, 2023
Publication date	Oct 14, 2025
Grant date	Oct 14, 2025

Abstract

Methods for encoding a video sequence into a bitstream and decoding a bitstream to output one or more pictures for a video stream. An exemplary method includes: receiving a video sequence; encoding one or more pictures of the video sequence; and generating a bitstream associated with the encoded pictures, wherein the encoding comprises: predicting chroma samples within a current block based on luma samples corresponding to the chroma samples by a plurality of cross-component residual models (CCRMs).

First claim

What is claimed is:

1. A method for encoding a video sequence into a bitstream, the method comprising:
receiving a video sequence;
encoding one or more pictures of the video sequence; and
generating a bitstream associated with the encoded pictures,
wherein the encoding comprises:
predicting chroma samples within a current block based on luma samples corresponding to the chroma samples by a plurality of cross-component residual models (CCRMs).

2. The method according to claim 1 , wherein the chroma samples are predicted based on the luma samples corresponding to the chroma samples by the plurality of CCRMs in response to a determination that the chroma samples are to be predicted with more than one CCRM.

3. The method according to claim 1 , wherein predicting the chroma samples based on the luma samples corresponding to the chroma samples comprises:
classifying the chroma samples into a plurality of classes, wherein the plurality of CCRMs corresponding to the plurality of classes are trained based on the chroma samples and corresponding luma samples, respectively; and
generating, by the plurality of CCRMs, a predicted chroma value of a target chroma sample of the chroma samples based on a luma sample corresponding to the target chroma sample.

4. The method according to claim 3 , wherein classifying the chroma samples into the plurality of classes comprises:
classifying an objective chroma sample into one of the plurality of classes based on a predicted luma value of a luma sample corresponding to the objective chroma sample.

5. The method according to claim 4 , wherein the objective chroma sample is classified into one of the plurality of classes based on a comparison between the predicted luma value of the luma sample and a threshold, the threshold being associated with predicted luma values or reconstructed luma values of at least a part of the luma samples within the current block.

6. The method according to claim 3 , wherein the encoding further comprises:
fusing the predicted chroma value of the target chroma sample with an original predicted chroma value of the target chroma sample to obtain a finalized predicted chroma value, the original predicted chroma value being inter-predicted with respect to a reference picture or generated by intra block copy (IBC).

7. The method according to claim 6 , wherein the encoding further comprises:
generating a residual chroma value of the target chroma sample based on the finalized predicted chroma value.

8. The method according to claim 6 , wherein the encoding further comprises:
filtering the finalized predicted chroma value by a low pass filter to obtain a filtered predicted chroma value of the target chroma sample.

9. The method according to claim 3 , wherein the encoding further comprises:
filtering the predicted chroma value by a low pass filter to obtain a filtered predicted chroma value of the target chroma sample; and
fusing the filtered predicted chroma value of the target chroma sample with an original predicted chroma value of the target chroma sample to obtain a finalized predicted chroma value, the original predicted chroma value being inter-predicted with respect to a reference picture or generated by intra block copy (IBC).

10. A method for decoding a bitstream to output one or more pictures for a video stream, the method comprising:
receiving a bitstream; and
decoding, using coded information of the bitstream, one or more pictures,
wherein the decoding comprises:
predicting chroma samples within a current block based on luma samples corresponding to the chroma samples by a plurality of cross-component residual models (CCRMs).

11. The method according to claim 10 , wherein the chroma samples are predicted based on the luma samples corresponding to the chroma samples by the plurality of CCRMs in response to a determination that the chroma samples are to be predicted with more than one CCRM.

12. The method according to claim 10 , wherein predicting the chroma samples based on the luma samples corresponding to the chroma samples comprises:
classifying the chroma samples into a plurality of classes, wherein the plurality of CCRMs corresponding to the plurality of classes are trained based on the chroma samples and corresponding luma samples, respectively; and
generating, by the plurality of CCRMs, a predicted chroma value of a target chroma sample of the chroma samples based on a luma sample corresponding to the target chroma sample.

13. The method according to claim 12 , wherein classifying the chroma samples into the plurality of classes comprises:
classifying an objective chroma sample into one of the plurality of classes based on a predicted luma value of a luma sample corresponding to the objective chroma sample.

14. The method according to claim 13 , wherein the objective chroma sample is classified into one of the plurality of classes based on a comparison between the predicted luma value of the luma sample and a threshold, the threshold being associated with predicted luma values or reconstructed luma values of at least a part of the luma samples within the current block.

15. The method according to claim 12 , wherein the decoding further comprises:
fusing the predicted chroma value of the target chroma sample with an original predicted chroma value of the target chroma sample to obtain a finalized predicted chroma value, the original predicted chroma value being inter-predicted with respect to a reference picture or generated by intra block copy (IBC).

16. The method according to claim 15 , wherein the decoding further comprises:
receiving a residual chroma value of the target chroma sample; and
generating a chroma value of the target chroma sample based on the residual chroma value and the finalized predicted chroma value.

17. The method according to claim 15 , wherein the decoding further comprises:
filtering the finalized predicted chroma value by a low pass filter to obtain a filtered predicted chroma value of the target chroma sample.

18. The method according to claim 15 , wherein the decoding further comprises:
filtering the predicted chroma value by a low pass filter to obtain a filtered predicted chroma value of the target chroma sample; and
fusing the filtered predicted chroma value of the target chroma sample with an original predicted chroma value of the target chroma sample to obtain a finalized predicted chroma value, the original predicted chroma value being inter-predicted with respect to a reference picture or generated by intra block copy (IBC).

19. A method of storing a bitstream of a video, the method comprising:
receiving a video sequence comprising one or more pictures;
generating a bitstream associated with the one or more pictures, wherein the generating comprises: predicting chroma samples within a current block based on luma samples corresponding to the chroma samples by a plurality of cross-component residual models (CCRMs); and
storing the bitstream in a non-transitory computer-readable storage medium.

20. The method according to claim 19 , wherein predicting the chroma samples based on the luma samples corresponding to the chroma samples comprises:
classifying the chroma samples into a plurality of classes, wherein the plurality of CCRMs corresponding to the plurality of classes are trained based on the chroma samples and corresponding luma samples, respectively; and
generating, by the plurality of CCRMs, a predicted chroma value of a target chroma sample of the chroma samples base

Assignees

• Alibaba China Co Ltd

Inventors

• Li Xinwei
• Chen Jie
• Ye Yan
• Liao Ru-Ling

Classifications

• H04N19/186 Primary

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

• H04N19/176

  the region being a block, e.g. a macroblock · CPC title

• H04N19/593

  involving spatial prediction techniques · CPC title

• H04N19/117

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

• H04N19/132 Primary

  Sampling, masking or truncation of coding units, e.g. adaptive resampling, frame skipping, frame interpolation or high-frequency transform coefficient masking · CPC title