US 11,863,756 B2
Image encoding and decoding apparatus and method using artificial intelligence
Quockhanh Dinh, Suwon-si (KR); and Kwangpyo Choi, Suwon-si (KR)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Feb. 22, 2022, as Appl. No. 17/677,414.
Application 17/677,414 is a continuation of application No. PCT/KR2022/002486, filed on Feb. 21, 2022.
Claims priority of application No. 10-2021-0023695 (KR), filed on Feb. 22, 2021; application No. 10-2021-0123369 (KR), filed on Sep. 15, 2021; and application No. 10-2021-0157089 (KR), filed on Nov. 15, 2021.
Prior Publication US 2022/0272352 A1, Aug. 25, 2022
Int. Cl. H04N 19/137 (2014.01); H04N 19/43 (2014.01); H04N 19/51 (2014.01); H04N 19/124 (2014.01); H04N 19/91 (2014.01)
CPC H04N 19/137 (2014.11) [H04N 19/124 (2014.11); H04N 19/43 (2014.11); H04N 19/51 (2014.11); H04N 19/91 (2014.11)] 9 Claims
OG exemplary drawing
 
1. An image decoding method using artificial intelligence (AI), the image decoding method comprising:
obtaining feature data of a current optical flow and feature data of current differential data from a bitstream corresponding to a current image;
applying feature data of a previous optical flow to a first preprocessing neural network;
obtaining a first concatenation result by concatenating the feature data of the current optical flow and feature data obtained from the first preprocessing neural network;
obtaining the current optical flow by applying the first concatenation result to a neural-network-based first decoder;
obtaining the current differential data by applying the feature data of the current differential data to a neural-network-based second decoder; and
reconstructing the current image using the current differential data and a current predicted image generated from a previous reconstructed image based on the current optical flow.