US 12,388,974 B2
Method for image processing and apparatus for implementing the same
Elie Mora, Malakoff (FR); Mohsen Abdoli, Rennes (FR); and Thomas Guionnet, Rennes (FR)
Assigned to ATEME, Velizy Villacoublay (FR)
Filed by ATEME, Velizy Villacoublay (FR)
Filed on Sep. 16, 2022, as Appl. No. 17/946,442.
Application 17/946,442 is a continuation of application No. 16/815,567, filed on Mar. 11, 2020, granted, now 11,451,768, issued on Sep. 20, 2022.
Claims priority of application No. 19305293 (EP), filed on Mar. 12, 2019.
Prior Publication US 2023/0009360 A1, Jan. 12, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 19/103 (2014.01); G06F 17/16 (2006.01); G06N 7/01 (2023.01); G06T 7/11 (2017.01); G06T 7/90 (2017.01)
CPC H04N 19/103 (2014.11) [G06F 17/16 (2013.01); G06N 7/01 (2023.01); G06T 7/11 (2017.01); G06T 7/90 (2017.01); G06T 2207/10016 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising, by a processor of an encoder side:
performing a Derived Intra Mode at Decoder (DIMD) image processing method for processing a current pixel block of an image; and
providing, to a decoder side, control information indicating that the DIMD image processing method has been used by the encoder side for processing the current pixel block of the image,
wherein the image is divided into a plurality of pixel blocks which are processed according to a processing sequence,
and wherein the DIMD image processing method comprises, for the current pixel block of the image:
determining an application area comprising a set of pixels in blocks preceding the current pixel block in the processing sequence;
performing a gradient analysis on at least one pixel of the application area;
selecting at least two intra prediction video coding modes among a plurality of intra prediction video coding modes usable for processing the current pixel block, wherein at least one of the selected intra prediction video coding modes is selected based on the gradient analysis;
determining a plurality of predictors of the current pixel block based on the at least two selected intra prediction video coding modes; and
generating a predictor of the current pixel block based on the determined plurality of predictors.