Generating and applying editing presets
In implementations of systems for generating and applying editing presets, a computing device implements a preset system to detect objects depicted in a digital image that is displayed in a user interface of an application for editing digital content. Input data is received describing an edited region of the digital image and properties of an editing operation performed in the edited region. The preset system identifies a particular detected object of the detected objects based on a bounding box of the particular detected object and an area of the edited region. An additional digital image is edited by applying the properties of the editing operation to a detected object that is depicted in the additional digital image based on a classification of the detected object and a classification of the particular detected object.
1. A method implemented by a computing device, the method comprising:
generating, by the computing device, input data based on user interaction detected via a user interface to edit a first digital image, the input data describing an edited region of the first digital image and a property of an editing operation performed in the edited region;
generating, by the computing device, a classification of a first object included in the edited region using machine learning;
generating, by the computing device, a preset based on the classification, the editing operation, and the property of the editing operation performed in the edited region; and
editing, by the computing device, a second object in a second digital image by applying the preset with the property to the second object.
2. The method as described in claim 1 , further comprising outputting the preset for display in the user interface, the present being selectable via the user interface to initiate the image editing operation using the property to the second object in the second digital image based on the classification.
3. The method as described in claim 2 , further comprising describing the classification of the second detected object in a extensible metadata platform document.
4. The method as described in claim 2 , further comprising determining a preset group for the preset based on a type of machine learning based mask used to segment the edited region of the first digital image, the edited region being selectable as a mask within the user interface that includes one or more first detected objects in the one or more classifications.
5. The method as described in claim 1 , wherein the classification of the second object is similar to the classification of the first object.
6. The method as described in claim 1 , wherein the second digital image is edited automatically and without user intervention.
7. The method as described in claim 1 , wherein the second digital image is edited in response to a user interaction in the user interface of the application for editing digital content.
8. The method as described in claim 7 , wherein the user interaction selects an indication of the editing operation from a list of relevant presets displayed in the user interface based on the classification of the first object.
9. The method as described in claim 1 , wherein the first object is identified based on an area of overlap between a bounding box surrounding the first object and the area of the edited region.
10. The method as described in claim 1 , wherein the edited region is segmented by a machine learning based mask generated by the application for editing digital content.
11. A system comprising:
a detection module implemented at least partially in hardware of a computing device to:
receive image data describing a digital image that is displayed in a user interface of an application for editing digital content; and
by a machine-learning model detect objects depicted in the first digital image;
a relevancy module implemented at least partially in the hardware of the computing device to identify presets, based on classifications of the detected objects; and
an interface module implemented at least partially in the hardware of the computing device to:
generate input data based on user interaction detected via a user interface to edit a first digital image, the input data describing an edited region of the first digital image and a property of an editing operation performed in the edited region;
generate a classification of a first object included in the edited region using machine learning;
generate, a preset based on the classification, the editing operation, and the property of the editing operation performed in the edited region; and
edit a second object in a second digital image by applying the preset with the property to the second object.
12. The system as described in claim 11 , wherein the classification of the second object is similar to the classification of the first object.
13. The system as described in claim 11 , wherein the edited region is segmented by a machine learning based mask generated by the application for editing digital content.
14. The system as described in claim 11 , wherein the first object is identified based on an area of overlap between a bounding box surrounding the first object and the area of the edited region.
15. The system as described in claim 11 , wherein the second digital image is edited automatically and without user intervention.
16. The system as described in claim 11 , wherein the second digital image is edited in response to a user interaction in the user interface of the application for editing digital content.
17. One or more non-transitory computer-readable storage media comprising instructions stored thereon that, responsive to execution by a computing device, causes the computing device to perform operations including:
detecting, objects depicted in a digital image that is displayed in a user interface of an application for editing digital content;
generating input data based on user interaction detected via a user interface to edit a first digital image, the input data describing an edited region of the first digital image and a property of an editing operation performed in the edited region;
generating a classification of a first object included in the edited region using machine learning;
generating a preset based on the classification, the editing operation, and the property of the editing operation performed in the edited region; and
editing a second object in a second digital image by applying the preset with the property to the second object.
18. The one or more non-transitory computer-readable storage media of claim 17 , wherein the classification of the second object is similar to a classification of the first object.
19. The one or more non-transitory computer-readable storage media of claim 17 , wherein the second digital image is edited automatically and without user intervention.
20. The one or more non-transitory computer-readable storage media of claim 17 , wherein the edited region is segmented by a machine learning based mask generated by the application for editing digital content.