US 12,323,633 B2
Deep prediction refinement
Franck Galpin, Thorigne-Fouillard (FR); Philippe Bordes, Laille (FR); Thierry Dumas, Rennes (FR); Karam Naser, Mouazé (FR); and Pavel Nikitin, Rennes (FR)
Assigned to InterDigital Madison Patent Holdings, SAS, Paris (FR)
Appl. No. 18/026,401
Filed by InterDigital Madison Patent Holdings, SAS, Paris (FR)
PCT Filed Sep. 14, 2021, PCT No. PCT/EP2021/075156
§ 371(c)(1), (2) Date Mar. 15, 2023,
PCT Pub. No. WO2022/058293, PCT Pub. Date Mar. 24, 2022.
Claims priority of application No. 20306029 (EP), filed on Sep. 15, 2020; application No. 20306603 (EP), filed on Dec. 18, 2020; and application No. 21305320 (EP), filed on Mar. 16, 2021.
Prior Publication US 2024/0031611 A1, Jan. 25, 2024
Int. Cl. H04N 19/85 (2014.01); H04N 19/176 (2014.01)
CPC H04N 19/85 (2014.11) [H04N 19/176 (2014.11)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
obtaining a first motion-compensated region for a block of a picture and obtaining a second region for the block;
providing as input to a main branch of a neural network the first motion-compensated region and the second region;
providing as input to a skip connection of the neural network a tensor that concatenates the first motion-compensated region and the second region;
obtaining from the skip connection a combination of the tensor with an output of a layer of the main branch of the neural network, wherein obtaining the combination includes one of: concatenating the tensor with the output of the layer of the main branch or performing a convolution on the tensor and adding the convoluted tensor to the output of the layer of the main branch;
performing a convolution on the combination obtained from the skip connection;
obtaining a prediction for the block based on an output of the convolution performed on the combination obtained from the skip connection; and
encoding the block based on the prediction.