Granted Patent B2

US 12,462,519 · App. 18/058,575 · Granted Nov 4, 2025

Inventors: Luis Figueroa (San Jose, CA); Zhe Lin (Fremont, CA); Zhihong Ding (Fremont, CA); Scott Cohen (Sunnyvale, CA)

Assignee: Adobe Inc.

G06V10/255G06F3/04842G06F3/04845G06T11/60G06V10/82

Abstract

Claims (62)

1 . A computer-implemented method comprising:

receiving a digital image from a client device;

detecting, utilizing a shadow detection neural network, an object portrayed in the digital image;

detecting, utilizing the shadow detection neural network, a shadow portrayed in the digital image;

generating, utilizing the shadow detection neural network, an object-shadow pair prediction that associates the shadow with the object;

providing the digital image for display within a graphical user interface of the client device; and

providing, for display within the graphical user interface in response to detecting a selection of the object, a first visual indication of the selection of the object and a second visual indication that the shadow is included in the selection based on the object-shadow pair prediction.

2 . The computer-implemented method of claim 1 , further comprising:

generating, utilizing the shadow detection neural network, an object mask for the object; and

generating, utilizing the shadow detection neural network, a shadow mask for the shadow.

3 . The computer-implemented method of claim 2 , wherein generating, utilizing the shadow detection neural network, the object-shadow pair prediction that associates the shadow with the object comprises generating, utilizing the shadow detection neural network, the object-shadow pair prediction based on the object mask and the shadow mask.

4 . The computer-implemented method of claim 1 , wherein:

providing the first visual indication of the selection of the object comprises highlighting the object within the digital image; and

providing the second visual indication that the shadow is included in the selection comprises highlighting the shadow within the digital image.

5 . The computer-implemented method of claim 1 ,

further comprising, in response to receiving the selection of the object, providing, for display within the graphical user interface, a suggestion to add the shadow to the selection,

wherein providing the second visual indication indicating the shadow is included in the selection comprises providing the second visual indication in response to receiving an additional user interaction for including the shadow in the selection.

6 . The computer-implemented method of claim 1 , further comprising:

receiving one or more user interactions for modifying the digital image by modifying the object portrayed in the digital image; and

modifying the digital image by modifying the object and the shadow in accordance with the one or more user interactions based on the object-shadow pair prediction.

7 . The computer-implemented method of claim 1 , wherein:

detecting, utilizing the shadow detection neural network, the object portrayed in the digital image comprises detecting, utilizing the shadow detection neural network, a plurality of objects portrayed in the digital image;

detecting, utilizing the shadow detection neural network, the shadow portrayed in the digital image comprises detecting, utilizing the shadow detection neural network, a plurality of shadows portrayed in the digital image; and

generating, utilizing the shadow detection neural network, the object-shadow pair prediction that associates the shadow with the object, the object-shadow pair prediction that associates each object from the plurality of objects with a shadow from the plurality of shadows cast by the object within the digital image.

8 . A non-transitory computer-readable medium storing instructions thereon that, when executed by at least one processor, cause the at least one processor to perform operations comprising:

generating, utilizing a shadow detection neural network, object masks for a plurality of objects portrayed in a digital image;

generating, utilizing the shadow detection neural network, shadow masks for a plurality of shadows portrayed in the digital image;

determining, utilizing the shadow detection neural network, an association between each shadow from the plurality of shadows and each object from the plurality of objects using the object masks and the shadow masks;

providing the digital image for display within a graphical user interface of a client device; and

providing, for display within the graphical user interface in response to detecting a selection of an object from the plurality of objects, a first visual indication of the selection of the object and a second visual indication that a shadow from the plurality of shadows is included in the selection based on determining the association between each shadow and each object.

9 . The non-transitory computer-readable medium of claim 8 , wherein, generating, utilizing the shadow detection neural network, the object masks for the plurality of objects portrayed in the digital image comprises generating, via a first stage of the shadow detection neural network and for each object of the plurality of objects, an object mask corresponding to the object and a combined object mask corresponding to other objects of the plurality of objects.

10 . The non-transitory computer-readable medium of claim 9 , wherein:

the operations further comprise generating, for each object of the plurality of objects, a second stage input by combining the object masks corresponding to the object, the combined object mask corresponding to the other objects, and the digital image; and

generating, utilizing the shadow detection neural network, the shadow masks for the plurality of shadows portrayed in the digital image comprises generating, via a second stage of the shadow detection neural network, the shadow masks for the plurality of shadows using the second stage input for each object.

11 . The non-transitory computer-readable medium of claim 8 , wherein generating, utilizing the shadow detection neural network, the shadow masks for the plurality of shadows portrayed in the digital image comprises generating, utilizing the shadow detection neural network and for each shadow portrayed in the digital image, a shadow mask corresponding to the shadow and a combined shadow mask corresponding to other shadows of the plurality of shadows.

12 . The non-transitory computer-readable medium of claim 11 , wherein determining, utilizing the shadow detection neural network, the association between each shadow and each object using the object masks and the shadow masks comprises determining the association between each shadow and each object utilizing the shadow mask and the combined shadow mask generated for each shadow.

13 . The non-transitory computer-readable medium of claim 8 , wherein the operations further comprise providing, to the client device, an object-shadow pair prediction that provides object-shadow pairs using the association between each shadow and each object.

14 . The non-transitory computer-readable medium of claim 8 , wherein the operations further comprise:

receiving one or more user interactions to move the object within the digital image; and

modifying, in response to receiving the one or more user interactions, the digital image by moving the object and the shadow associated with the object within the digital image.

15 . The non-transitory computer-readable medium of claim 8 , wherein the operations further comprise:

receiving one or more user interactions to delete the object from the digital image; and

modifying, in response to receiving the one or more user interactions, the digital image by removing the object and the shadow associated with the object from the digital image.

16 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise:

generating, before receiving the one or more user interactions to delete the object, a first content fill for the object and a second content fill for the shadow associated with the object utilizing a content-aware fill machine learning model; and

providing the first content fill and the second content fill within the digital image so that removal of the object exposes the first content fill and removal of the shadow exposes the second content fill.

17 . A system comprising:

at least one memory device comprising a shadow detection neural network; and

at least one processor configured to cause the system to:

generate, utilizing an instance segmentation model of the shadow detection neural network, object masks for a plurality of objects portrayed in a digital image;

determine input to a shadow segmentation model of the shadow detection neural network by combining the object masks for the plurality of objects and the digital image;

generate, utilizing the shadow segmentation model and the input, shadow masks for shadows associated with the plurality of objects within the digital image; and

provide, for display on a graphical user interface of a client device, a visual indication associating an object from the plurality of objects and a shadow from the shadows utilizing the shadow masks.

18 . The system of claim 17 , wherein the at least one processor is further configured to cause the system to:

generate the object masks for the plurality of objects by generating an object mask corresponding to each object of the plurality of objects;

generate combined object masks for the plurality of objects, each combined object mask corresponding to two or more objects from the plurality of objects; and

determine the input to the shadow segmentation model by combining the combined object masks with the object masks and the digital image.

19 . The system of claim 18 , wherein combining the combined object masks with the object masks and the digital image comprises, for each object of the plurality of objects, concatenating an object mask corresponding to the object, a combined object mask corresponding to other objects of the plurality of objects, and the digital image.

20 . The system of claim 18 , wherein the at least one processor is further configured to cause the system to:

generate the shadow masks for the shadows by generating a shadow mask corresponding to each shadow of the shadows;

generate, utilizing the shadow segmentation model and the input, combined shadow masks for the shadows, each combined shadow mask corresponding to two or more shadows from the shadows; and

determine associations between the plurality of objects and the shadows utilizing the shadow masks and the combined shadow masks.

Assignments (1)

Continuity (1)

References Cited (231)