US 12,323,738 B2
Generating an alpha channel
Ran Oz, Maccabim (IL); Eyal Gavish, Los Altos, CA (US); and Rima Gandlin, Los Altos, CA (US)
Assigned to Cavendish Capital LLC, Wilmington, DE (US)
Filed by Cavendish Capital LLC, Wilmington, DE (US)
Filed on Mar. 1, 2022, as Appl. No. 17/653,026.
Application 17/653,026 is a continuation in part of application No. 17/539,036, filed on Nov. 30, 2021, abandoned.
Application 17/653,026 is a continuation in part of application No. 17/304,378, filed on Jun. 20, 2021, granted, now 11,805,157.
Application 17/539,036 is a continuation of application No. 17/249,468, filed on Mar. 2, 2021, granted, now 11,792,367.
Application 17/304,378 is a continuation of application No. 17/249,468, filed on Mar. 2, 2021, granted, now 11,792,367.
Claims priority of provisional application 63/201,713, filed on May 10, 2021.
Claims priority of provisional application 63/199,014, filed on Dec. 1, 2020.
Claims priority of provisional application 63/081,860, filed on Sep. 22, 2020.
Claims priority of provisional application 63/023,836, filed on May 12, 2020.
Prior Publication US 2022/0191431 A1, Jun. 16, 2022
Int. Cl. G06T 7/11 (2017.01); G06F 3/01 (2006.01); G06N 3/04 (2023.01); G06N 3/045 (2023.01); G06T 7/70 (2017.01); G06T 15/04 (2011.01); G06T 15/20 (2011.01); G06T 17/20 (2006.01); G06T 19/00 (2011.01); G06T 19/20 (2011.01); H04N 7/14 (2006.01); H04N 7/15 (2006.01)
CPC H04N 7/157 (2013.01) [G06F 3/013 (2013.01); G06N 3/04 (2013.01); G06N 3/045 (2023.01); G06T 7/11 (2017.01); G06T 7/70 (2017.01); G06T 15/04 (2013.01); G06T 15/20 (2013.01); G06T 15/205 (2013.01); G06T 17/20 (2013.01); G06T 19/00 (2013.01); G06T 19/20 (2013.01); H04N 7/144 (2013.01); H04N 7/147 (2013.01); H04N 7/152 (2013.01); G06T 2200/08 (2013.01); G06T 2207/30201 (2013.01); G06T 2219/2004 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating alpha channel information related to a person, the method comprises:
generating the alpha channel information related to the person by an alpha channel neural network; wherein the alpha channel machine learning process is trained using ground truth alpha channel information that is associated with background information;
wherein the ground-truth alpha channel information is generated by:
obtaining input images of the person; wherein each image comprises the person and an arbitrary background;
repeating, for each input image of the input images, converting the input image, by a portrait matting predictor, to (a) a first colored background image that comprises the person and a background of a first color, and (b) a second colored background image that comprises the person and a background of a second color;
wherein the first color differs from the second color;
wherein the training comprises:
repeating, for each input image of the input images:
i. determining person properties within the input image;
ii. generating, by the alpha channel neural network, a first image, the first image is of the first avatar of the person with the first colored background and having the person properties;
iii. comparing first alpha channel information related to the first image to ground-truth alpha channel information related to the first colored background image to provide a first comparison result;
iv. generating, by the alpha channel neural network, a second image, the second image is of the second avatar of the person with the second colored background and having the person properties; and
v. comparing second alpha channel information related to the second image to ground-truth alpha channel information related to the second colored background image to provide a second comparison result.