US 11,676,347 B2
Virtual try-on systems for spectacles using reference frames
David Goldberg, New York, NY (US); Andrew Garrison, New York, NY (US); Adam Greenberg, New York, NY (US); Paul Johnson, New York, NY (US); and Paul Mackey, New York, NY (US)
Assigned to Warby Parker Inc., New York, NY (US)
Filed by Warby Parker Inc., New York, NY (US)
Filed on Apr. 9, 2021, as Appl. No. 17/226,454.
Claims priority of provisional application 63/010,421, filed on Apr. 15, 2020.
Prior Publication US 2021/0327148 A1, Oct. 21, 2021
Int. Cl. G06T 19/00 (2011.01); G06F 3/0482 (2013.01); G06T 7/194 (2017.01); G06T 7/11 (2017.01); G06T 7/70 (2017.01); G06Q 30/0601 (2023.01); G06T 7/60 (2017.01); G06V 40/16 (2022.01)
CPC G06T 19/006 (2013.01) [G06F 3/0482 (2013.01); G06Q 30/0643 (2013.01); G06T 7/11 (2017.01); G06T 7/194 (2017.01); G06T 7/60 (2013.01); G06T 7/70 (2017.01); G06V 40/171 (2022.01); G06T 2200/24 (2013.01); G06T 2207/30201 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
capturing, by a client device, a first image of a user, the first image including a reference token for a user-wearable item, the reference token being worn by the first user in the first image and having a known three-dimensional model;
automatically generating, by the client device, a three-dimensional model of a face of the user from the first image of the user, the three-dimensional model of the face of the user including dimensions based on the known three-dimensional model of the reference token;
displaying, by the client device, images of multiple user-wearable items for the user;
receiving an input from the user, the input indicative of a selected user-wearable item from the user-wearable items on display, the selected user-wearable item having an associated three-dimensional model;
segmenting, by the client device, the first image to separate the reference token from a background comprising a portion of a physiognomy of the user;
replacing, by the client device, a segment for the reference token in the first image with an image for the selected user-wearable item in a second image of the user based on the three-dimensional model of the face of the user and the three-dimensional model of the selected user-wearable item; and
displaying, by the client device, the second image of the user.