公开(公告)号：US12056791B2

公开(公告)日：2024-08-06

申请号：US17407863

申请日：2021-08-20

Applicant: Adobe Inc.

Inventor： Harshit Agrawal ,  Venkatrayalu Krishnamurthy Logashwar

IPC: G06T11/00 ,  G06F3/04845 ,  G06F16/53 ,  G06F18/24 ,  G06N20/00 ,  G06V20/80

CPC classification number: G06T11/00 ,  G06F3/04845 ,  G06F16/53 ,  G06F18/24 ,  G06N20/00 ,  G06V20/80 ,  G06T2200/24

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly generating image layers and determining layer labels utilizing a machine learning approach. For example, the disclosed systems utilize an image segmentation machine learning model to segment the digital image and identify individual objects depicted within the digital image. Additionally, in some embodiments, the disclosed systems determine object classifications for the depicted objects by utilizing an object classification machine learning model. In some cases, the disclosed systems further generate image layers for the digital image by generating a separate layer for each identified object (or for groups of similar objects). In certain embodiments, the disclosed systems also determine layer labels for the image layers according to the object classifications of the respective objects depicted in each of the image layers.

公开(公告)号：US20230059007A1

公开(公告)日：2023-02-23

申请号：US17407863

申请日：2021-08-20

Applicant: Adobe Inc.

Inventor： Harshit Agrawal ,  Venkatrayalu Krishnamurthy Logashwar

IPC: G06T11/00 ,  G06K9/62 ,  G06K9/00 ,  G06F3/0484 ,  G06N20/00 ,  G06F16/53

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly generating image layers and determining layer labels utilizing a machine learning approach. For example, the disclosed systems utilize an image segmentation machine learning model to segment the digital image and identify individual objects depicted within the digital image. Additionally, in some embodiments, the disclosed systems determine object classifications for the depicted objects by utilizing an object classification machine learning model. In some cases, the disclosed systems further generate image layers for the digital image by generating a separate layer for each identified object (or for groups of similar objects). In certain embodiments, the disclosed systems also determine layer labels for the image layers according to the object classifications of the respective objects depicted in each of the image layers.