US 12,470,681 B2
Method and apparatus for generating compact multiplane images
Neus Sabater, Betton (FR); Julia Navarro, Palma (ES); Julien Fleureau, Rennes (FR); and Guillaume Boisson, Pleumeleuc (FR)
Assigned to InterDigital CE Patent Holdings, SAS, Paris (FR)
Appl. No. 18/272,472
Filed by InterDigital CE Patent Holdings, SAS, Paris (FR)
PCT Filed Jan. 11, 2022, PCT No. PCT/EP2022/050469
§ 371(c)(1), (2) Date Jul. 14, 2023,
PCT Pub. No. WO2022/152709, PCT Pub. Date Jul. 21, 2022.
Claims priority of application No. 21305034 (EP), filed on Jan. 14, 2021.
Prior Publication US 2024/0098235 A1, Mar. 21, 2024
Int. Cl. H04N 13/161 (2018.01); H04N 13/00 (2018.01); H04N 13/139 (2018.01); H04N 13/156 (2018.01); H04N 13/194 (2018.01)
CPC H04N 13/161 (2018.05) [H04N 13/139 (2018.05); H04N 13/156 (2018.05); H04N 13/194 (2018.05); H04N 2013/0081 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A method for generating a multiplane image, comprising:
acquiring a multi-view image of a 3D scene comprising n views, indexed from 1 to n;
generating a first multiplane image by inputting views of the multi-view image indexed by 1 to n−1 and a set of at least one parameter in a convolutional neural network trained to generate a multiplane image representative of a multi-view image, the set of at least one parameter being used in a penalization term of the convolutional neural network to determine a redundancy of information between layers of the multiplane image;
synthetizing the n-th view based on the first multiplane image;
updating the set of at least one parameter responsive to a comparison between the synthetized n-th view and the n-th view of the multi-view image; and
generating a second multiplane image by inputting the n views of the multi-view image and the updated set of at least one parameter in the convolutional neural network.