US 12,462,407 B2
Depth estimation method in an immersive video context
Joël Jung, Paris (FR)
Assigned to Tencent Cloud Europe (France) SAS, Paris (FR)
Filed by Tencent Cloud Europe (France) SAS, Paris (FR)
Filed on Sep. 12, 2023, as Appl. No. 18/367,337.
Application 18/367,337 is a continuation of application No. PCT/IB2021/000725, filed on Oct. 5, 2021.
Prior Publication US 2023/0419519 A1, Dec. 28, 2023
Int. Cl. G06T 7/50 (2017.01); H04N 13/161 (2018.01); H04N 13/172 (2018.01); H04N 13/00 (2018.01)
CPC G06T 7/50 (2017.01) [H04N 13/161 (2018.05); H04N 13/172 (2018.05); G06T 2207/10016 (2013.01); H04N 2013/0081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of synthesizing an image, the method comprising:
receiving, from a server, a coded video stream corresponding to different views of a scene acquired by a plurality of cameras;
identifying one or more derivable depth blocks of a target depth map corresponding to an image of the coded video stream, wherein the target depth map represents a depth of the one or more derivable depth blocks;
determining, for each of the one or more derivable depth blocks, a respective depth derivation operation to derive the depth of the respective derivable depth block;
deriving each of the one or more derivable depth blocks based on the depth derivation operation of the respective derivable depth block and a depth of at least one reference depth block that is associated with the respective derivable depth block, the depth derivation operation being applied to the depth of the at least one reference depth block that is included in a depth map of a reference image in the coded video stream;
obtaining the target depth map corresponding to the image by executing, for each of the one or more derivable depth blocks, the respective depth derivation operation of the respective derivable depth block; and
synthesizing a new image according to the target depth map and at least one decoded image from the coded video stream.