Google llc (20240346631). BYSTANDER AND ATTACHED OBJECT REMOVAL simplified abstract
Contents
BYSTANDER AND ATTACHED OBJECT REMOVAL
Organization Name
Inventor(s)
Orly Liba of Mountain View CA (US)
Pedro Velez of Mountain View CA (US)
Siyang Li of Mountain View CA (US)
Huizhong Chen of Mountain View CA (US)
Marcel Puyat of Mountain View CA (US)
Yanan Bao of Mountain View CA (US)
BYSTANDER AND ATTACHED OBJECT REMOVAL - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240346631 titled 'BYSTANDER AND ATTACHED OBJECT REMOVAL
The abstract describes a media application that detects a bystander in an initial image and generates a bystander box around them. Localizer boxes are then created to encompass the bystander and any objects attached to them. These boxes are aggregated to form an aggregated box. A segmenter is applied to the initial image based on the aggregated box to segment the bystander and objects, generating a bystander mask. An inpainted image is then created by replacing the pixels within the bystander mask with background pixels from the initial image.
- Media application detects and segments a bystander in an image
- Generates bystander box and localizer boxes for bystander and attached objects
- Aggregates boxes to form an aggregated box
- Applies segmenter to segment bystander and objects
- Creates inpainted image by replacing pixels within the bystander mask
Potential Applications: - Image editing software - Surveillance systems - Social media platforms
Problems Solved: - Efficiently isolating and removing individuals from images - Enhancing image editing capabilities - Improving object recognition in images
Benefits: - Simplifies editing process - Enhances privacy protection in images - Streamlines object segmentation tasks
Commercial Applications: Title: Advanced Image Editing Technology for Media Applications This technology can be utilized in image editing software, surveillance systems, and social media platforms to improve object recognition and editing capabilities. It has the potential to enhance user experience and streamline image processing tasks in various industries.
Questions about the technology: 1. How does this technology improve object recognition in images? 2. What are the potential privacy implications of using this technology in surveillance systems?
Original Abstract Submitted
a media application detects a bystander in an initial image. the media application generates a bystander box that includes the bystander, wherein all pixels for the bystander are within the bystander box. the media application generates localizer boxes that encompass the bystander and one or more objects that are attached to the bystander. the media application aggregates the bystander box and one or more of the localizer boxes to form an aggregated box. the media application applies a segmenter to the initial image, based on the aggregated box, to segment the bystander and the one or more objects from the initial image to generate a bystander mask, wherein the bystander mask includes a subset of pixels within the aggregated box. the media application generates an inpainted image that replaces all pixels within the bystander mask with pixels that match a background in the initial image.
