Granted Patent B2

US 12,670,643 · App. 18/746,866 · Granted Jun 30, 2026

Inventors: Itamar Berger (Hod Hasharon, IL); Gal Dudovitch (Tel Aviv, IL); Gal Sasson (Kibbutz Ayyelet Hashahar, IL); Ma'ayan Mishin Shuvi (Tel Aviv, IL); Matan Zohar (Rishon LeZion, IL)

Assignee: Snap Inc.

G06T19/006

Abstract

Claims (77)

1 . A method comprising:

applying one or more virtual items to an object depicted in a video;

determining that a first portion of the object overlaps a second portion of the object;

in response to the determining, adjusting one or more attributes of the one or more virtual items, the adjusting comprising:

detecting an image on the second portion; and

modifying an aspect ratio of the image on the second portion in response to detecting a gesture.

2 . The method of claim 1 , further comprising:

receiving the video that includes a depiction of the object wearing a fashion item, the second portion comprising the fashion item;

generating a segmentation of the fashion item; and

applying the one or more virtual items to the fashion item based on the segmentation of the fashion item worn.

3 . The method of claim 1 , wherein the second portion comprises a shirt, further comprising:

detecting a hand of the object in the video;

determining a position of the hand of the object in relation to a position of the shirt; and

adjusting a color of the shirt based on the position of the hand.

4 . The method of claim 1 , wherein the first portion of the object comprises a hand, further comprising:

determining that a position of the hand overlaps a first portion of a segmentation of the second portion of the object; and

in response to determining that the position of the hand overlaps the first portion, adjusting a color of the second portion to be a first color.

5 . The method of claim 4 , further comprising:

determining that the position of the hand overlaps a second portion of the segmentation of the second portion of the object; and

in response to determining that the position of the hand overlaps the second portion, adjusting the color of the second portion to be a second color.

6 . The method of claim 1 , further comprising:

generating a segmentation of the object depicted in the video;

identifying a background in the video based on the segmentation;

detecting a hand of the object in the video;

determining a position of the hand of the object in relation to a position of the segmentation; and

adjusting the identified background of the video based on the position of the hand of the object.

7 . The method of claim 6 , further comprising:

moving the one or more virtual items along a given direction away from a position of the hands, the one or more virtual items being moved along an arm of the object.

8 . The method of claim 1 , comprising:

detecting movement of hands of the object depicted in the video along a given direction; and

in response detecting movement of hands of the object depicted in the video along the given direction, modifying an animation comprising the one or more virtual items.

9 . The method of claim 1 , further comprising:

determining a pose of the object depicted in the video; and

adjusting a pose of the one or more virtual items to match the pose of the object depicted in the video.

10 . The method of claim 1 , further comprising:

detecting a physical logo or emblem on the second portion;

determining a pose of the object depicted in the video; and

generating, as the one or more virtual items, an augmented reality version of the physical logo or emblem.

11 . The method of claim 10 , further comprising:

adjusting a pose of the augmented reality version of the physical logo or emblem to match the pose of the object.

12 . The method of claim 11 , further comprising:

overlaying the augmented reality version of the physical logo or emblem comprising the adjusted pose on top of the physical logo or emblem on the second portion.

13 . The method of claim 1 , further comprising:

detecting a pose of a hand of the object depicted in the video;

generating, as the one or more virtual items, an augmented reality version of the hand in the detected pose; and

displaying the augmented reality version of the hand in the detected pose on the second portion.

14 . The method of claim 1 , wherein detecting the gesture comprises:

detecting a pair of hands positioned over the image; and

determining movement of a first hand of the pair of hands in relation to a second hand of the pair of hands, wherein movement determined to be in a first manner causes the aspect ratio of the image to be modified by a first amount, and wherein movement determined to be in a second manner causes the aspect ratio of the image to be modified by a second amount.

15 . A system comprising:

at least one processor of a device; and

a memory component having instructions stored thereon, when executed by the at least one processor, causes the at least one processor to perform operations comprising:

applying one or more virtual items to an object depicted in a video;

determining that a first portion of the object overlaps a second portion of the object; and

in response to the determining, adjusting one or more attributes of the one or more virtual items, the adjusting comprising:

detecting an image on the second portion; and

modifying an aspect ratio of the image on the second portion in response to detecting a gesture.

16 . The system of claim 15 , the operations further comprising:

receiving the video that includes a depiction of the object wearing a fashion item, the second portion comprising the fashion item;

generating a segmentation of the fashion item; and

applying the one or more virtual items to the fashion item based on the segmentation of the fashion item worn.

17 . The system of claim 15 , wherein the second portion comprises a shirt, the operations further comprising:

detecting a hand of the object in the video;

determining a position of the hand of the object in relation to a position of the shirt; and

adjusting a color of the shirt based on the position of the hand.

18 . The system of claim 15 , wherein the first portion of the object comprises a hand, the operations further comprising:

determining that a position of the hand overlaps a first portion of a segmentation of the second portion of the object; and

in response to determining that the position of the hand overlaps the first portion, adjusting a color of the second portion to be a first color.

19 . A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by at least one processor of a device, cause the at least one processor to perform operations comprising:

applying one or more virtual items to an object depicted in a video;

determining that a first portion of the object overlaps a second portion of the object; and

in response to the determining, adjusting one or more attributes of the one or more virtual items, the adjusting comprising:

detecting an image on the second portion; and

modifying an aspect ratio of the image on the second portion in response to detecting a gesture.

20 . The non-transitory computer-readable storage medium of claim 19 , the operations comprising:

detecting a physical logo or emblem on the second portion; and

generating, as the one or more virtual items, an augmented reality version of the physical logo or emblem.

Assignments (1)

Continuity (3)

References Cited (400)