18190513. UTILIZING A GENERATIVE MACHINE LEARNING MODEL AND GRAPHICAL USER INTERFACE FOR CREATING MODIFIED DIGITAL IMAGES FROM AN INFILL SEMANTIC MAP simplified abstract (Adobe Inc.)

UTILIZING A GENERATIVE MACHINE LEARNING MODEL AND GRAPHICAL USER INTERFACE FOR CREATING MODIFIED DIGITAL IMAGES FROM AN INFILL SEMANTIC MAP

Organization Name

Adobe Inc.

Inventor(s)

Qing Liu of Santa Clara CA (US)

Jianming Zhang of Campbell CA (US)

Krishna Kumar Singh of San Jose CA (US)

Scott Cohen of Sunnyvale CA (US)

Zhe Lin of Fremont CA (US)

UTILIZING A GENERATIVE MACHINE LEARNING MODEL AND GRAPHICAL USER INTERFACE FOR CREATING MODIFIED DIGITAL IMAGES FROM AN INFILL SEMANTIC MAP - A simplified explanation of the abstract

This abstract first appeared for US patent application 18190513 titled 'UTILIZING A GENERATIVE MACHINE LEARNING MODEL AND GRAPHICAL USER INTERFACE FOR CREATING 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, particularly focusing on human subjects.

• Utilizes generative machine learning models to create modified digital images of human subjects.
• Performs infill modifications or human inpainting to complete or enhance digital images.
• Reposes subjects within digital images to generate modified versions.
• Enables facial expression transfer and animations for modified digital images or animations.

Potential Applications

This technology can be applied in various fields such as digital art, photography, entertainment industry, and social media platforms.

Problems Solved

This innovation addresses the need for efficient and effective editing of digital images, especially those portraying human subjects, by leveraging artificial intelligence and machine learning algorithms.

Benefits

The technology streamlines the process of modifying digital images, enhances the visual appeal of human subjects in images, and enables creative expression through facial expression transfer and animations.

Commercial Applications

"AI-Enhanced Digital Image Editing for Human Subjects: Market Trends and Opportunities"

This technology can be utilized by graphic designers, photographers, social media influencers, and entertainment companies to enhance and manipulate digital images of human subjects for various commercial purposes.

Prior Art

There have been advancements in AI-based image editing tools, but the specific focus on scene-based editing for human subjects sets this innovation apart.

Frequently Updated Research

Stay updated on the latest developments in AI-driven image editing techniques and applications to maximize the potential of this technology.

Questions about AI-Enhanced Digital Image Editing

Question 1

How does this technology improve the efficiency of digital image editing processes?

This technology utilizes AI and machine learning to automate and enhance the editing of digital images, particularly focusing on human subjects, resulting in more efficient and effective editing workflows.

Question 2

What are the key factors that differentiate this scene-based editing approach from traditional image editing techniques?

The use of generative machine learning models, infill modifications, reposing of subjects, and facial expression transfer sets this technology apart by offering advanced and specialized editing capabilities for digital images portraying human subjects.

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.