公开(公告)号：US11282208B2

公开(公告)日：2022-03-22

申请号：US16231746

申请日：2018-12-24

Applicant: Adobe Inc.

Inventor： Scott Cohen ,  Long Mai ,  Jun Hao Liew ,  Brian Price

IPC: G06T7/12 ,  G06T7/194 ,  G06K9/32 ,  G06T3/40

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing scale-diverse segmentation neural networks to analyze digital images at different scales and identify different target objects portrayed in the digital images. For example, in one or more embodiments, the disclosed systems analyze a digital image and corresponding user indicators (e.g., foreground indicators, background indicators, edge indicators, boundary region indicators, and/or voice indicators) at different scales utilizing a scale-diverse segmentation neural network. In particular, the disclosed systems can utilize the scale-diverse segmentation neural network to generate a plurality of semantically meaningful object segmentation outputs. Furthermore, the disclosed systems can provide the plurality of object segmentation outputs for display and selection to improve the efficiency and accuracy of identifying target objects and modifying the digital image.

公开(公告)号：US20230177824A1

公开(公告)日：2023-06-08

申请号：US18161666

申请日：2023-01-30

Applicant: Adobe Inc.

Inventor： Brian Price ,  Scott Cohen ,  Mai Long ,  Jun Hao Liew

IPC: G06V10/82 ,  G06N3/084 ,  G06T7/11 ,  G06V10/26 ,  G06V10/44 ,  G06F18/40 ,  G06N3/045 ,  G06N5/01 ,  G06V10/94 ,  G06V10/20

CPC classification number: G06V10/82 ,  G06N3/084 ,  G06T7/11 ,  G06V10/26 ,  G06V10/454 ,  G06F18/40 ,  G06N3/045 ,  G06N5/01 ,  G06V10/945 ,  G06V10/255 ,  G06N3/044

Abstract: Systems and methods are disclosed for selecting target objects within digital images utilizing a multi-modal object selection neural network trained to accommodate multiple input modalities. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators corresponding to various input modalities. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user inputs corresponding to different input modalities to select target objects in digital images. Specifically, the disclosed systems and methods can transform user inputs into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

公开(公告)号：US11568627B2

公开(公告)日：2023-01-31

申请号：US16376704

申请日：2019-04-05

Applicant: Adobe Inc.

Inventor： Brian Price ,  Scott Cohen ,  Mai Long ,  Jun Hao Liew

IPC: G06V10/20 ,  G06N3/08 ,  G06K9/62 ,  G06N3/04 ,  G06T7/11 ,  G06N5/00 ,  G06V10/26 ,  G06V10/44 ,  G06V10/24

Abstract: Systems and methods are disclosed for selecting target objects within digital images utilizing a multi-modal object selection neural network trained to accommodate multiple input modalities. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators corresponding to various input modalities. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user inputs corresponding to different input modalities to select target objects in digital images. Specifically, the disclosed systems and methods can transform user inputs into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

公开(公告)号：US20190236394A1

公开(公告)日：2019-08-01

申请号：US16376704

申请日：2019-04-05

Applicant: Adobe Inc.

Inventor： Brian Price ,  Scott Cohen ,  Mai Long ,  Jun Hao Liew

IPC: G06K9/32 ,  G06K9/46

CPC classification number: G06K9/3241 ,  G06K9/4628 ,  G06K2009/366

Abstract: Systems and methods are disclosed for selecting target objects within digital images utilizing a multi-modal object selection neural network trained to accommodate multiple input modalities. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators corresponding to various input modalities. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user inputs corresponding to different input modalities to select target objects in digital images. Specifically, the disclosed systems and methods can transform user inputs into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

公开(公告)号：US12254633B2

公开(公告)日：2025-03-18

申请号：US17655493

申请日：2022-03-18

Applicant: Adobe Inc.

Inventor： Scott Cohen ,  Long Mai ,  Jun Hao Liew ,  Brian Price

IPC: G06T7/12 ,  G06T3/4046 ,  G06T7/194 ,  G06V10/20 ,  G06V10/44 ,  G06V10/82 ,  G06V10/24

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing scale-diverse segmentation neural networks to analyze digital images at different scales and identify different target objects portrayed in the digital images. For example, in one or more embodiments, the disclosed systems analyze a digital image and corresponding user indicators (e.g., foreground indicators, background indicators, edge indicators, boundary region indicators, and/or voice indicators) at different scales utilizing a scale-diverse segmentation neural network. In particular, the disclosed systems can utilize the scale-diverse segmentation neural network to generate a plurality of semantically meaningful object segmentation outputs. Furthermore, the disclosed systems can provide the plurality of object segmentation outputs for display and selection to improve the efficiency and accuracy of identifying target objects and modifying the digital image.

公开(公告)号：US20220207745A1

公开(公告)日：2022-06-30

申请号：US17655493

申请日：2022-03-18

Applicant: Adobe Inc.

Inventor： Scott Cohen ,  Long Mai ,  Jun Hao Liew ,  Brian Price

IPC: G06T7/12 ,  G06T7/194 ,  G06T3/40 ,  G06V10/25

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing scale-diverse segmentation neural networks to analyze digital images at different scales and identify different target objects portrayed in the digital images. For example, in one or more embodiments, the disclosed systems analyze a digital image and corresponding user indicators (e.g., foreground indicators, background indicators, edge indicators, boundary region indicators, and/or voice indicators) at different scales utilizing a scale-diverse segmentation neural network. In particular, the disclosed systems can utilize the scale-diverse segmentation neural network to generate a plurality of semantically meaningful object segmentation outputs. Furthermore, the disclosed systems can provide the plurality of object segmentation outputs for display and selection to improve the efficiency and accuracy of identifying target objects and modifying the digital image.