US 12,143,578 B2
Neural network based filter in video coding
Philippe Bordes, Cesson-Sevigne (FR); Franck Galpin, Cesson-Sevigne (FR); Thierry Dumas, Cesson-Sevigne (FR); Pavel Nikitin, Rennes (FR); and Fabrice Urban, Cesson-Sevigne (FR)
Assigned to InterDigital CE Patent Holdings, SAS, Paris (FR)
Appl. No. 17/925,479
Filed by InterDigital CE Patent Holdings, SAS, Paris (FR)
PCT Filed May 24, 2021, PCT No. PCT/EP2021/063771
§ 371(c)(1), (2) Date Nov. 15, 2022,
PCT Pub. No. WO2021/244884, PCT Pub. Date Dec. 9, 2021.
Claims priority of application No. 20305591 (EP), filed on Jun. 4, 2020; application No. 20306417 (EP), filed on Nov. 20, 2020; application No. 20306628 (EP), filed on Dec. 21, 2020; and application No. 21305444 (EP), filed on Apr. 7, 2021.
Prior Publication US 2023/0188713 A1, Jun. 15, 2023
Int. Cl. H04N 7/12 (2006.01); H04N 19/117 (2014.01); H04N 19/132 (2014.01); H04N 19/172 (2014.01); H04N 19/42 (2014.01)
CPC H04N 19/117 (2014.11) [H04N 19/132 (2014.11); H04N 19/172 (2014.11); H04N 19/42 (2014.11)] 16 Claims
OG exemplary drawing
 
1. A method, comprising:
accessing a version of reconstructed samples of a region of a picture;
generating a weight for each sample of a plurality of samples in said region based on said version of reconstructed samples of said region, using a neural network;
encoding an offset parameter in a bitstream, wherein neural network parameters of said neural network are not transmitted in said bitstream; and
filtering said plurality of samples in said region, wherein a sample of said plurality of samples in said region is adjusted based on a weight for said sample and said offset parameter for said region, and wherein said offset parameter for said region is scaled by said weight for said sample and said scaled offset is added to said sample to adjust said sample.