Invention Grant
- Patent Title: Generating class-agnostic object masks in digital images
-
Application No.: US17151111Application Date: 2021-01-15
-
Publication No.: US11587234B2Publication Date: 2023-02-21
- Inventor: Yinan Zhao , Brian Price , Scott Cohen
- Applicant: Adobe Inc.
- Applicant Address: US CA San Jose
- Assignee: Adobe Inc.
- Current Assignee: Adobe Inc.
- Current Assignee Address: US CA San Jose
- Agency: Keller Preece PLLC
- Main IPC: G06T7/11
- IPC: G06T7/11 ; G06T7/168 ; G06T9/00 ; G06T5/00 ; G06T7/181

Abstract:
The present disclosure relates to a class-agnostic object segmentation system that automatically detects, segments, and selects objects within digital images irrespective of object semantic classifications. For example, the object segmentation system utilizes a class-agnostic object segmentation neural network to segment each pixel in a digital image into an object mask. Further, in response to detecting a selection request of a target object, the object segmentation system utilizes a corresponding object mask to automatically select the target object within the digital image. In some implementations, the object segmentation system utilizes a class-agnostic object segmentation neural network to detect and automatically select a partial object in the digital image in response to a target object selection request.
Public/Granted literature
- US20220230321A1 GENERATING CLASS-AGNOSTIC OBJECT MASKS IN DIGITAL IMAGES Public/Granted day:2022-07-21
Information query