US 12,008,710 B2
Generating light-source-specific parameters for digital images using a neural network
Kalyan Sunkavalli, San Jose, CA (US); Yannick Hold-Geoffroy, San Jose, CA (US); Christian Gagne, Quebec City (CA); Marc-Andre Gardner, Quebec City (CA); and Jean-Francois Lalonde, Quebec City (CA)
Assigned to Adobe Inc., San Jose, CA (US); and Universite Laval, Quebec City (CA)
Filed by Adobe Inc., San Jose, CA (US); and Université Laval, Québec (CA)
Filed on Dec. 6, 2022, as Appl. No. 18/062,460.
Application 18/062,460 is a division of application No. 16/558,975, filed on Sep. 3, 2019, granted, now 11,538,216.
Prior Publication US 2023/0098115 A1, Mar. 30, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 15/00 (2011.01); G06N 3/08 (2023.01); G06T 7/50 (2017.01); G06T 7/60 (2017.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06T 15/50 (2011.01)
CPC G06T 15/506 (2013.01) [G06N 3/08 (2013.01); G06T 7/50 (2017.01); G06T 7/60 (2013.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06T 2200/24 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable medium storing computer-readable instructions which, when executed by at least one processing device, cause the at least one processing device to perform operations comprising:
extracting a latent feature vector from a digital image utilizing a first subset of common network layers of a source-specific-lighting-estimation-neural network;
extracting a common feature vector from the latent feature vector utilizing a second subset of common network layers of the source-specific-lighting-estimation-neural network; and
generating three-dimensional (“3D”) source-specific-lighting parameters based on the common feature vector utilizing parametric-specific-network layers of the source-specific-lighting-estimation-neural network by:
generating 3D-source-specific-distance parameters estimating one or more distances of one or more light sources from a reference point based on the latent feature vector utilizing distance-parametric-specific-network layers of the parametric-specific-network layers; and
generating source-specific-lighting parameters based on the common feature vector utilizing additional parametric-specific-network layers of the parametric-specific-network layers.