The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Dec. 05, 2023

Filed:

Jun. 03, 2021
Applicant:

Spree3d Corporation, Incline Village, NV (US);

Inventors:

Mohamed N. Moustafa, Metuchen, NJ (US);

Ahmed A. Ewais, New Cairo, EG;

Amr A. Ali, Cairo, EG;

Assignee:

Spree3D Corporation, Incline Village, NV (US);

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G06T 5/50 (2006.01); G06T 7/70 (2017.01); G06N 3/088 (2023.01); G06N 3/045 (2023.01);
U.S. Cl.
CPC ...
G06T 5/50 (2013.01); G06N 3/045 (2023.01); G06N 3/088 (2013.01); G06T 7/70 (2017.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20221 (2013.01); G06T 2207/30201 (2013.01);
Abstract

Apparati, methods, and computer readable media for inserting identity information from a source image () into a destination image (), while mimicking illumination of the destination image (). In an apparatus embodiment, an identity encoder () is configured to encode just identity information of the source image () and to produce an identity vector (), where the identity encoder () does not encode any pose information or illumination information of the source image (). A driver encoder () has two components: a pose encoder () configured to encode pose information of the destination image () and an illumination encoder () configured to separately encode illumination information of the destination image (), and to produce two vectors: a pose vector () and an illumination vector (). A neural network generator () is coupled to the identity encoder () and to the driver encoder (), and has three inputs: the identity vector (), the pose vector (), and the illumination vector (). The neural network generator () is configured to generate, in response to these three inputs, a composite image () comprising identity information of the source image () inserted into the destination image (), wherein the composite image has substantially the same illumination as the destination image.


Find Patent Forward Citations

Loading…