18190654. UTILIZING A WARPED DIGITAL IMAGE WITH A REPOSING MODEL TO SYNTHESIZE A MODIFIED DIGITAL IMAGE simplified abstract (Adobe Inc.)

UTILIZING A WARPED DIGITAL IMAGE WITH A REPOSING MODEL TO SYNTHESIZE A MODIFIED DIGITAL IMAGE

Organization Name

Adobe Inc.

Inventor(s)

Krishna Kumar Singh of San Jose CA (US)

Yijun Li of Seattle WA (US)

Jingwan Lu of Santa Clara CA (US)

Duygu Ceylan Aksit of Mountain View CA (US)

Yangtuanfeng Wang of London (GB)

Jimei Yang of Merced CA (US)

Tobias Hinz of Ulm (DE)

UTILIZING A WARPED DIGITAL IMAGE WITH A REPOSING MODEL TO SYNTHESIZE A MODIFIED DIGITAL IMAGE - A simplified explanation of the abstract

This abstract first appeared for US patent application 18190654 titled 'UTILIZING A WARPED DIGITAL IMAGE WITH A REPOSING MODEL TO SYNTHESIZE A MODIFIED DIGITAL IMAGE

The present disclosure involves systems, methods, and computer-readable media that use artificial intelligence to modify digital images through scene-based editing.

• 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 portraying humans.
• Reposes subjects within digital images to generate modified versions.
• Performs facial expression transfer and animations on human subjects within digital images.

1. 1. 1. Potential Applications:

This technology could be used in the fields of photography, graphic design, and entertainment industries for creating realistic and enhanced digital images of human subjects.

1. 1. 1. Problems Solved:

This technology addresses the need for efficient and effective ways to modify digital images, especially those portraying human subjects, by leveraging artificial intelligence and machine learning models.

1. 1. 1. Benefits:

- Enhances the quality and realism of digital images portraying human subjects. - Streamlines the editing process for digital images. - Allows for creative and innovative modifications to be made to digital images.

1. 1. 1. Commercial Applications:

The technology could be applied in industries such as advertising, fashion, and film production for creating visually appealing and engaging content.

1. 1. 1. Prior Art:

Prior art related to this technology may include image editing software and techniques, as well as advancements in artificial intelligence and machine learning for image processing.

1. 1. 1. Frequently Updated Research:

Research on the advancements in generative machine learning models and artificial intelligence for image editing and understanding could be relevant to this technology.

1. 1. 1. 1. Questions about Scene-Based Editing Using AI:

1. How does this technology improve the process of editing digital images? 2. What are the potential ethical considerations when using AI for modifying digital images?

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.