18188671. NEURAL COMPOSITING BY EMBEDDING GENERATIVE TECHNOLOGIES INTO NON-DESTRUCTIVE DOCUMENT EDITING WORKFLOWS simplified abstract (Adobe Inc.)
Contents
- 1 NEURAL COMPOSITING BY EMBEDDING GENERATIVE TECHNOLOGIES INTO NON-DESTRUCTIVE DOCUMENT EDITING WORKFLOWS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 NEURAL COMPOSITING BY EMBEDDING GENERATIVE TECHNOLOGIES INTO NON-DESTRUCTIVE DOCUMENT EDITING WORKFLOWS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Key Features and Innovation
- 1.6 Potential Applications
- 1.7 Problems Solved
- 1.8 Benefits
- 1.9 Commercial Applications
- 1.10 Prior Art
- 1.11 Frequently Updated Research
- 1.12 Questions about Image Modification Technology
- 1.13 Original Abstract Submitted
NEURAL COMPOSITING BY EMBEDDING GENERATIVE TECHNOLOGIES INTO NON-DESTRUCTIVE DOCUMENT EDITING WORKFLOWS
Organization Name
Inventor(s)
Alexandru Vasile Costin of Monte Sereno CA (US)
Oliver Brdiczka of San Jose CA (US)
Aliakbar Darabi of Newcastle WA (US)
Davis Taylor Brown of Seattle WA (US)
David Davenport Bourgin of Brooklyn NY (US)
NEURAL COMPOSITING BY EMBEDDING GENERATIVE TECHNOLOGIES INTO NON-DESTRUCTIVE DOCUMENT EDITING WORKFLOWS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18188671 titled 'NEURAL COMPOSITING BY EMBEDDING GENERATIVE TECHNOLOGIES INTO NON-DESTRUCTIVE DOCUMENT EDITING WORKFLOWS
Simplified Explanation
The patent application describes a method for modifying images using a scene graph and an image generation neural network.
- Obtaining an original image, a scene graph, and a description of a modification.
- Updating the scene graph based on the modification description.
- Generating a modified image using an image generation neural network and the updated scene graph.
Key Features and Innovation
- Utilizes a scene graph to describe elements of an image and modifications.
- Incorporates content from the original image and modification description in the modified image.
- Employs an image generation neural network for creating the modified image.
Potential Applications
This technology can be used in various fields such as graphic design, virtual reality, and image editing software.
Problems Solved
- Simplifies the process of modifying images.
- Allows for precise control over image modifications.
- Enhances the efficiency of image editing tasks.
Benefits
- Streamlines image editing workflows.
- Enables the creation of realistic modified images.
- Facilitates the implementation of complex image modifications.
Commercial Applications
The technology can be applied in industries such as advertising, entertainment, and e-commerce for creating visually appealing and customized images.
Prior Art
There may be existing technologies that utilize scene graphs and neural networks for image editing, but the specific combination described in this patent application may be unique.
Frequently Updated Research
There may be ongoing research in the fields of computer vision and image processing that could impact the development and implementation of this technology.
Questions about Image Modification Technology
Question 1
How does the scene graph contribute to the modification of images? The scene graph provides a structured representation of the elements in the image and the modifications to be applied, facilitating the generation of a modified image.
Question 2
What role does the image generation neural network play in creating modified images? The image generation neural network uses the updated scene graph to generate a modified image that incorporates content from the original image and the specified modifications.
Original Abstract Submitted
One or more aspects of the method, apparatus, and non-transitory computer readable medium include obtaining an original image, a scene graph describing elements of the original image, and a description of a modification to the original image. The one or more aspects further include updating the scene graph based on the description of the modification. The one or more aspects further include generating a modified image using an image generation neural network based on the updated scene graph, wherein the modified image incorporates content based on the original image and the description of the modification.