18190544. GENERATING A MODIFIED DIGITAL IMAGE UTILIZING A HUMAN INPAINTING MODEL simplified abstract (Adobe Inc.)

GENERATING A MODIFIED DIGITAL IMAGE UTILIZING A HUMAN INPAINTING MODEL

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)

Qing Liu of Santa Clara CA (US)

Jianming Zhang of Campbell CA (US)

Zhe Lin of Fremont CA (US)

GENERATING A MODIFIED DIGITAL IMAGE UTILIZING A HUMAN INPAINTING MODEL - A simplified explanation of the abstract

This abstract first appeared for US patent application 18190544 titled 'GENERATING A MODIFIED DIGITAL IMAGE UTILIZING A HUMAN INPAINTING MODEL

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

• 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 a digital image to generate modified digital images.
• Performs facial expression transfer and animations to create modified digital images or animations.

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

Problems Solved: This technology addresses the need for efficient and automated ways to modify digital images, especially those portraying human subjects, to enhance their visual appeal and realism.

Benefits: The technology offers a faster and more accurate way to edit digital images, saving time and effort for photographers and graphic designers. It also allows for creative enhancements and transformations of human subjects in images.

Commercial Applications: This technology can be utilized in photo editing software, social media platforms, and digital art applications to provide users with advanced editing tools for modifying digital images of human subjects.

Prior Art: There have been advancements in image editing software and artificial intelligence technologies that have enabled the modification of digital images, but the specific focus on scene-based editing and image understanding for human subjects sets this technology apart.

Frequently Updated Research: Research in the field of generative machine learning models and image understanding continues to evolve, leading to further advancements in digital image modification techniques.

Questions about Scene-Based Editing Using AI: 1. How does this technology differentiate itself from traditional image editing software? This technology stands out by utilizing artificial intelligence for scene-based editing and image understanding, specifically focusing on human subjects in digital images.

2. What are the potential ethical considerations when using AI to modify digital images of human subjects? Ethical considerations may arise regarding the authenticity and consent of individuals portrayed in modified digital images, highlighting the importance of responsible use of AI technology in image editing.

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.