View source for 18190500. UTILIZING A GENERATIVE MACHINE LEARNING MODEL TO CREATE MODIFIED DIGITAL IMAGES FROM AN INFILL SEMANTIC MAP simplified abstract (Adobe Inc.)

=UTILIZING A GENERATIVE MACHINE LEARNING MODEL TO CREATE MODIFIED DIGITAL IMAGES FROM AN INFILL SEMANTIC MAP=


==Organization Name==

[[:Category:Adobe Inc.|Adobe Inc.]]


[[Category:Adobe Inc.]]

==Inventor(s)==

[[:Category:Qing Liu of Santa Clara CA (US)|Qing Liu of Santa Clara CA (US)]][[Category:Qing Liu of Santa Clara CA (US)]]

[[:Category:Jianming Zhang of Campbell CA (US)|Jianming Zhang of Campbell CA (US)]][[Category:Jianming Zhang of Campbell CA (US)]]

[[:Category:Krishna Kumar Singh of San Jose CA (US)|Krishna Kumar Singh of San Jose CA (US)]][[Category:Krishna Kumar Singh of San Jose CA (US)]]

[[:Category:Scott Cohen of Sunnyvale CA (US)|Scott Cohen of Sunnyvale CA (US)]][[Category:Scott Cohen of Sunnyvale CA (US)]]

[[:Category:Zhe Lin of Fremont CA (US)|Zhe Lin of Fremont CA (US)]][[Category:Zhe Lin of Fremont CA (US)]]

==UTILIZING A GENERATIVE MACHINE LEARNING MODEL TO CREATE MODIFIED DIGITAL IMAGES FROM AN INFILL SEMANTIC MAP - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18190500 titled 'UTILIZING A GENERATIVE MACHINE LEARNING MODEL TO CREATE MODIFIED DIGITAL IMAGES FROM AN INFILL SEMANTIC MAP

The present disclosure involves systems, methods, and computer-readable media that use artificial intelligence for scene-based editing of digital images. This includes generating modified digital images of human subjects through generative machine learning models and performing various modifications such as infill modifications and reposing of subjects within the images.

* Utilizes generative machine learning models for creating modified digital images of human subjects
* Performs infill modifications and human inpainting for completing digital images
* Reposes subjects within digital images to generate modified versions
* Facilitates facial expression transfer and animations for creating modified digital images or animations

== Potential Applications ==
This technology can be used in various fields such as photography, graphic design, entertainment industry, and social media platforms for enhancing and manipulating digital images of human subjects.

== Problems Solved ==
This technology addresses the need for efficient and automated editing of digital images, especially those portraying human subjects, by utilizing artificial intelligence and machine learning algorithms to generate modified versions with various enhancements.

== Benefits ==
The benefits of this technology include faster and more accurate editing of digital images, the ability to create realistic modifications of human subjects, and the automation of complex editing tasks for improved efficiency.

== Commercial Applications ==
"AI-Enhanced Digital Image Editing: Revolutionizing the Way We Modify Images"

This technology has commercial applications in industries such as advertising, fashion, and digital art where high-quality and visually appealing images of human subjects are essential for marketing and branding purposes.

== Prior Art ==
There are existing technologies in the field of image editing and manipulation, but the use of artificial intelligence for scene-based editing and modifications of digital images, particularly those portraying human subjects, is a novel and innovative approach.

== Frequently Updated Research ==
Ongoing research in the field of artificial intelligence and image processing continues to improve the capabilities and accuracy of scene-based editing tools for digital images, with a focus on enhancing the realism and quality of modified images.

== Questions about Scene-Based Editing Using AI ==
=== Question 1 ===
How does this technology differentiate itself from traditional image editing software?

Traditional image editing software relies on manual input and predefined tools for editing digital images, while this technology uses artificial intelligence and machine learning algorithms to automate and enhance the editing process, particularly for images portraying human subjects.

=== Question 2 ===
What are the potential ethical considerations associated with using AI for modifying digital images of human subjects?

The use of AI for editing digital images of human subjects raises concerns about privacy, consent, and the potential for creating misleading or harmful representations. It is important to consider ethical guidelines and regulations when utilizing this technology in various applications.


==Original Abstract Submitted==

The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via scene-based editing using image understanding facilitated by artificial intelligence. For example, in one or more embodiments the disclosed systems utilize generative machine learning models to create modified digital images portraying human subjects. In particular, the disclosed systems generate modified digital images by performing infill modifications to complete a digital image or human inpainting for portions of a digital image that portrays a human. Moreover, in some embodiments, the disclosed systems perform reposing of subjects portrayed within a digital image to generate modified digital images. In addition, the disclosed systems in some embodiments perform facial expression transfer and facial expression animations to generate modified digital images or animations.



[[Category:G06T5/00]]
[[Category:G06T7/11]]
[[Category:G06T11/60]]
[[Category:G06V10/764]]
[[Category:G06V10/82]]
[[Category:G06V20/70]]
[[Category:CPC_G06T5/005]]