	US 12,225,221 B2
	Ultra light models and decision fusion for fast video coding
Shan Li, Fremont, CA (US); Claudionor Coelho, Redwood City, CA (US); In Suk Chong, Mountain View, CA (US); and Aki Kuusela, Palo Alto, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Appl. No. 17/779,380
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Dec. 23, 2019, PCT No. PCT/US2019/068279 § 371(c)(1), (2) Date May 24, 2022, PCT Pub. No. WO2021/107965, PCT Pub. Date Jun. 3, 2021.
Claims priority of provisional application 62/940,272, filed on Nov. 26, 2019.
Prior Publication US 2023/0007284 A1, Jan. 5, 2023
Int. Cl. H04N 19/107 (2014.01); H04N 19/11 (2014.01); H04N 19/124 (2014.01); H04N 19/149 (2014.01); H04N 19/159 (2014.01); H04N 19/176 (2014.01); H04N 19/436 (2014.01); H04N 19/593 (2014.01)

CPC H04N 19/436 (2014.11) [H04N 19/11 (2014.11); H04N 19/124 (2014.11); H04N 19/149 (2014.11); H04N 19/159 (2014.11); H04N 19/176 (2014.11); H04N 19/593 (2014.11)]

19 Claims

1. A method for encoding a current block of video using intra-prediction, comprising:

obtaining, using a machine-learning (ML) model, an ML intra-prediction mode;

obtaining a most-probable intra-prediction mode from amongst available intra-prediction modes for encoding the current block;

selecting, as an encoding intra-prediction mode, one of the ML intra-prediction mode or the most-probable intra-prediction mode, wherein the selecting is based on relative reliabilities of the ML intra-prediction mode and the most-probable intra-prediction mode, wherein the relative reliabilities are values of a decision matrix generated during training of the ML model;

encoding, in a compressed bitstream, the encoding intra-prediction mode; and

encoding the current block using the encoding intra-prediction mode.