US 12,192,445 B2
Inter prediction method based on variable coefficient deep learning
Je Won Kang, Seoul (KR); Na Young Kim, Seoul (KR); Jung Kyung Lee, Seoul (KR); Seung Wook Park, Yongin-si (KR); and Wha Pyeong Lim, Hwaseong-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 Mar. 27, 2023, as Appl. No. 18/126,623.
Application 18/126,623 is a continuation of application No. PCT/KR2021/013218, filed on Sep. 28, 2021.
Claims priority of application No. 10-2020-0126111 (KR), filed on Sep. 28, 2020; and application No. 10-2021-0127795 (KR), filed on Sep. 28, 2021.
Prior Publication US 2023/0239462 A1, Jul. 27, 2023
Int. Cl. H04N 19/105 (2014.01); H04N 19/109 (2014.01); H04N 19/139 (2014.01); H04N 19/159 (2014.01); H04N 19/176 (2014.01); H04N 19/513 (2014.01)
CPC H04N 19/105 (2014.11) [H04N 19/109 (2014.11); H04N 19/139 (2014.11); H04N 19/159 (2014.11); H04N 19/176 (2014.11); H04N 19/513 (2014.11)] 16 Claims
OG exemplary drawing
 
1. A video decoding method performed by a video decoding apparatus, the video decoding method comprising:
decoding variable coefficient values, an affine prediction flag, and an encoding mode from a bitstream, the affine prediction flag indicating whether affine motion prediction is applied to a current block, and the encoding mode being an encoding mode for motion information of the current block and indicating a merge mode or an advanced motion vector prediction (AMVP) mode;
generating a virtual reference frame based on reference frames by using an interpolation model, wherein a variable coefficient network included in the interpolation model is set with the variable coefficient values; and
generating a merge candidate of the current block based on the virtual reference frame and the reference frames when the encoding mode is the merge mode.