18500263. BACKGROUND SEPARATION FOR GUIDED GENERATIVE MODELS simplified abstract (Adobe Inc.)

From WikiPatents
Jump to navigation Jump to search

BACKGROUND SEPARATION FOR GUIDED GENERATIVE MODELS

Organization Name

Adobe Inc.

Inventor(s)

Sudeep Katakol of San Francisco CA (US)

Siddharth Iyer of San Francisco CA (US)

Aliakbar Darabi of Newcastle WA (US)

BACKGROUND SEPARATION FOR GUIDED GENERATIVE MODELS - A simplified explanation of the abstract

This abstract first appeared for US patent application 18500263 titled 'BACKGROUND SEPARATION FOR GUIDED GENERATIVE MODELS


  • Simplified Explanation: This patent application involves a method for generating an output image based on an input image and an approximate mask that indicates a foreground region. The output image includes the foreground region of the input image.
  • Key Features and Innovation:

- Obtaining an input image and an approximate mask indicating a foreground region. - Generating an unconditional mask of the foreground region based on the input image. - Creating a conditional mask of the foreground region based on the input image and the approximate mask. - Generating an output image based on the unconditional mask and the conditional mask.

  • Potential Applications:

- Image editing and manipulation software. - Foreground extraction in photography. - Augmented reality applications. - Video editing tools.

  • Problems Solved:

- Efficient foreground region extraction. - Improved image editing capabilities. - Enhanced visual effects in multimedia content.

  • Benefits:

- Accurate foreground region extraction. - Seamless integration of foreground elements into images. - Streamlined image editing workflows.

  • Commercial Applications:

"Foreground Region Extraction Technology for Image Editing and Augmented Reality Applications"

  • Questions about Foreground Region Extraction Technology:

1. How does this technology improve the accuracy of foreground region extraction in images? 2. What are the potential applications of this technology beyond image editing and photography?

  • Frequently Updated Research:

Stay updated on advancements in image processing algorithms for foreground extraction and image editing techniques.


Original Abstract Submitted

Embodiments of the present disclosure include obtaining an input image and an approximate mask that approximately indicates a foreground region of the input image. Some embodiments generate an unconditional mask of the foreground region based on the input image. A conditional mask of the foreground region is generated based on the input image and the approximate mask. Then, an output image is generated based on the unconditional mask and the conditional mask. In some cases, the output image includes the foreground region of the input image.