US 11,704,778 B2
Method for generating an adaptive multiplane image from a single high-resolution image
Diogo Carbonera Luvizon, São Paulo (BR); Henrique Fabricio Gagliardi, São Paulo (BR); and Otavio Augusto Bizetto Penatti, São Paulo (BR)
Assigned to SAMSUNG ELETRONICA DA AMAZONIA LTDA., Campinas (BR)
Filed by SAMSUNG ELETRÔNICA DA AMAZÔNIA LTDA., São Paulo (BR)
Filed on Mar. 15, 2021, as Appl. No. 17/201,516.
Claims priority of application No. 10 2020 027013 3 (BR), filed on Dec. 30, 2020.
Prior Publication US 2022/0207663 A1, Jun. 30, 2022
Int. Cl. G06T 5/00 (2006.01); G06T 7/55 (2017.01); G06T 5/30 (2006.01); G06T 7/13 (2017.01); G06T 7/50 (2017.01)
CPC G06T 5/005 (2013.01) [G06T 5/30 (2013.01); G06T 7/13 (2017.01); G06T 7/50 (2017.01); G06T 7/55 (2017.01); G06T 2207/20064 (2013.01); G06T 2207/20084 (2013.01)] 8 Claims
OG exemplary drawing
 
1. A method of generating an adaptive multiplane image (AMI) from a single image, comprising:
receiving the single image as an input;
generating a depth map by performing a depth estimation process;
performing adaptative slicing of the single image into partial image planes;
processing the partial image planes with occluded regions by inpainting; and
rearranging resulting image planes to form a AMI representation,
wherein the generating of the depth map comprises:
feeding the input to a Time-Frequency Decomposition (TFD) layer in a new feature map with half of an input resolution and with four times more features in a channel dimension;
applying a sequence of convolutional layers;
generating a new set of wavelet coefficients; and
transforming the new set of wavelet coefficients to the input resolution by an Inverse Time-Frequency Decomposition (I-TFD).