US 12,470,700 B2
Method and apparatus for video coding for improving predicted signals of intra prediction
Je Won Kang, Seoul (KR); Jung Kyung Lee, Seoul (KR); Na Young Kim, Seoul (KR); and Seung Wook Park, Yongin-si (KR)
Assigned to HYUNDAI MOTOR COMPANY, Seoul (KR); KIA CORPORATION, Seoul (KR); and EWHA UNIVERSITY—INDUSTRY COLLABORATION FOUNDATION, Seoul (KR)
Filed by HYUNDAI MOTOR COMPANY, Seoul (KR); KIA CORPORATION, Seoul (KR); and EWHA UNIVERSITY—INDUSTRY COLLABORATION FOUNDATION, Seoul (KR)
Filed on Aug. 31, 2023, as Appl. No. 18/240,888.
Application 18/240,888 is a continuation of application No. PCT/KR2022/002996, filed on Mar. 3, 2022.
Claims priority of application No. 10-2021-0028794 (KR), filed on Mar. 4, 2021; and application No. 10-2022-0026005 (KR), filed on Feb. 28, 2022.
Prior Publication US 2023/0412798 A1, Dec. 21, 2023
Int. Cl. H04N 19/11 (2014.01); H04N 19/119 (2014.01); H04N 19/176 (2014.01); H04N 19/42 (2014.01); H04N 19/593 (2014.01); H04N 19/70 (2014.01); H04N 19/91 (2014.01)
CPC H04N 19/11 (2014.11) [H04N 19/119 (2014.11); H04N 19/176 (2014.11); H04N 19/42 (2014.11); H04N 19/593 (2014.11); H04N 19/70 (2014.11); H04N 19/91 (2014.11)] 16 Claims
OG exemplary drawing
 
1. A video decoding apparatus comprising:
an entropy decoder configured to decode an intra prediction mode and residual values of a current block from a bitstream, decode a refinement flag, or determine the refinement flag, wherein the refinement flag indicates whether to apply a deep learning-based refinement model at a time of intra prediction of the current block;
an intra predictor configured to generate a prediction block of the current block using the intra prediction mode;
a signal refinement unit configured to generate a refined prediction block from the prediction block using the refinement model when the refinement flag is 1; and
an adder configured to generate a restored block of the current block by adding the residual values to the refined prediction block when the refinement flag is 1 or generate the restored block by adding the residual values to the prediction block when the refinement flag is 0,
wherein the refinement model is implemented using a deep learning model including a fixed coefficient-based network and is pre-trained to generate a refined prediction block approximating an original image of the current block.