US 12,335,469 B2
Adaptive filter intra prediction modes in image/video compression
Alexander Bokov, Mountian View, CA (US); and Hui Su, Sunnyvale, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Apr. 15, 2024, as Appl. No. 18/635,416.
Application 18/635,416 is a continuation of application No. 17/684,461, filed on Mar. 2, 2022, granted, now 11,979,564.
Application 17/684,461 is a continuation of application No. 16/999,109, filed on Aug. 21, 2020, granted, now 11,297,314, issued on Apr. 5, 2022.
Application 16/999,109 is a continuation of application No. 16/287,969, filed on Feb. 27, 2019, granted, now 10,778,972, issued on Sep. 15, 2020.
Prior Publication US 2024/0267514 A1, Aug. 8, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 19/11 (2014.01); H04N 19/117 (2014.01); H04N 19/184 (2014.01)
CPC H04N 19/11 (2014.11) [H04N 19/117 (2014.11); H04N 19/184 (2014.11)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable storage medium having stored thereon a compressed bitstream, wherein the compressed bitstream is configured for decoding by operations comprising:
identifying an adaptive intra-prediction mode indicative of at least a training region or a configuration of neighboring pixel locations, wherein the adaptive intra-prediction mode is one of a plurality of adaptive intra-prediction modes and wherein the training region neighbors a block and consists of reconstructed pixels;
determining filter coefficients used to obtain respective prediction pixels of neighboring pixels within the training region when applied according to the configuration of the neighboring pixels, wherein the filter coefficients minimize a function of differences, each difference being a respective difference between a pixel in the training region and a prediction of that pixel in the training region; and
generating a prediction block for the block by recursive extrapolations that use the filter coefficients by predicting each pixel of the prediction block by applying the filter coefficients to the configuration of neighboring pixels for the pixel being predicted.