18460365. MODIFYING DIGITAL IMAGES VIA MULTI-LAYERED SCENE COMPLETION FACILITATED BY ARTIFICIAL INTELLIGENCE simplified abstract (Adobe Inc.)

MODIFYING DIGITAL IMAGES VIA MULTI-LAYERED SCENE COMPLETION FACILITATED BY ARTIFICIAL INTELLIGENCE

Organization Name

Adobe Inc.

Inventor(s)

Daniil Pakhomov of San Jose CA (US)

Qing Liu of Santa Clara CA (US)

Zhihong Ding of Fremont CA (US)

Scott Cohen of Sunnyvale CA (US)

Zhe Lin of Fremont CA (US)

Jianming Zhang of Campbell CA (US)

Zhifei Zhang of San Jose CA (US)

Ohiremen Dibua of Newark NJ (US)

Mariette Souppe of San Jose CA (US)

Krishna Kumar Singh of San Jose CA (US)

Jonathan Brandt of Santa Cruz CA (US)

MODIFYING DIGITAL IMAGES VIA MULTI-LAYERED SCENE COMPLETION FACILITATED BY ARTIFICIAL INTELLIGENCE - A simplified explanation of the abstract

This abstract first appeared for US patent application 18460365 titled 'MODIFYING DIGITAL IMAGES VIA MULTI-LAYERED SCENE COMPLETION FACILITATED BY ARTIFICIAL INTELLIGENCE

Simplified Explanation

The patent application describes systems and methods that use artificial intelligence to modify digital images through multi-layered scene completion techniques. These systems can identify objects in an image, generate content fills for occluded areas, and allow users to interact with and manipulate the objects in the image.

• Systems modify digital images using multi-layered scene completion techniques facilitated by artificial intelligence.
• Images with occluded objects are pre-processed to generate content fills for the occluded areas.
• Users can interact with and manipulate objects in the image by moving or deleting them.
• The systems expose the content fills for occluded areas when objects are moved or deleted.

Key Features and Innovation

• Use of artificial intelligence for modifying digital images.
• Generation of content fills for occluded areas in images.
• User interaction to manipulate objects in the image.
• Exposing content fills for occluded areas when objects are moved or deleted.

Potential Applications

This technology can be used in various applications such as:

• Image editing software
• Augmented reality applications
• Virtual reality environments
• Gaming industry for scene completion and object manipulation

Problems Solved

• Addressing occluded objects in digital images.
• Providing a user-friendly way to manipulate objects in images.
• Enhancing the editing capabilities of digital images.

Benefits

• Improved image editing efficiency.
• Enhanced user experience in interacting with digital images.
• Increased flexibility in modifying and completing scenes in images.

Commercial Applications

Title: AI-Enhanced Image Editing Technology for Scene Completion and Object Manipulation This technology can be commercially used in:

• Photography and graphic design software
• Entertainment industry for special effects
• E-commerce for product image editing
• Advertising agencies for creative content creation

Prior Art

Information on prior art related to this technology is not provided in the abstract.

Frequently Updated Research

There is no information on frequently updated research relevant to this technology.

Questions about the Technology

Question 1

How does the artificial intelligence in the system identify and process occluded objects in digital images?

The artificial intelligence in the system uses advanced algorithms to analyze the digital image and identify areas where objects are occluded. It then generates content fills for these occluded areas based on the surrounding context and textures in the image.

Question 2

Can users customize the content fills generated by the system for occluded areas in digital images?

Yes, users can interact with the digital image and manipulate the objects to expose the content fills for occluded areas. They can move or delete objects to customize the scene according to their preferences.

Original Abstract Submitted

The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via multi-layered scene completion techniques facilitated by artificial intelligence. For instance, in some embodiments, the disclosed systems receive a digital image portraying a first object and a second object against a background, where the first object occludes a portion of the second object. Additionally, the disclosed systems pre-process the digital image to generate a first content fill for the portion of the second object occluded by the first object and a second content fill for a portion of the background occluded by the second object. After pre-processing, the disclosed systems detect one or more user interactions to move or delete the first object from the digital image. The disclosed systems further modify the digital image by moving or deleting the first object and exposing the first content fill for the portion of the second object.