公开(公告)号：US11335004B2

公开(公告)日：2022-05-17

申请号：US16988408

申请日：2020-08-07

Applicant: Adobe Inc.

Inventor： Zichuan Liu ,  Wentian Zhao ,  Shitong Wang ,  He Qin ,  Yumin Jia ,  Yeojin Kim ,  Xin Lu ,  Jen-Chan Chien

IPC: G06T7/11

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate refined segmentation masks for digital visual media items. For example, in one or more embodiments, the disclosed systems utilize a segmentation refinement neural network to generate an initial segmentation mask for a digital visual media item. The disclosed systems further utilize the segmentation refinement neural network to generate one or more refined segmentation masks based on uncertainly classified pixels identified from the initial segmentation mask. To illustrate, in some implementations, the disclosed systems utilize the segmentation refinement neural network to redetermine whether a set of uncertain pixels corresponds to one or more objects depicted in the digital visual media item based on low-level (e.g., local) feature values extracted from feature maps generated for the digital visual media item.

公开(公告)号：US20220245824A1

公开(公告)日：2022-08-04

申请号：US17660361

申请日：2022-04-22

Applicant: Adobe Inc.

Inventor： Zichuan Liu ,  Wentian Zhao ,  Shitong Wang ,  He Qin ,  Yumin Jia ,  Yeojin Kim ,  Xin Lu ,  Jen-Chan Chien

IPC: G06T7/11

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate refined segmentation masks for digital visual media items. For example, in one or more embodiments, the disclosed systems utilize a segmentation refinement neural network to generate an initial segmentation mask for a digital visual media item. The disclosed systems further utilize the segmentation refinement neural network to generate one or more refined segmentation masks based on uncertainly classified pixels identified from the initial segmentation mask. To illustrate, in some implementations, the disclosed systems utilize the segmentation refinement neural network to redetermine whether a set of uncertain pixels corresponds to one or more objects depicted in the digital visual media item based on low-level (e.g., local) feature values extracted from feature maps generated for the digital visual media item.

公开(公告)号：US11676283B2

公开(公告)日：2023-06-13

申请号：US17660361

申请日：2022-04-22

Applicant: Adobe Inc.

Inventor： Zichuan Liu ,  Wentian Zhao ,  Shitong Wang ,  He Qin ,  Yumin Jia ,  Yeojin Kim ,  Xin Lu ,  Jen-Chan Chien

IPC: G06T7/11

CPC classification number: G06T7/11 ,  G06T2207/20084

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate refined segmentation masks for digital visual media items. For example, in one or more embodiments, the disclosed systems utilize a segmentation refinement neural network to generate an initial segmentation mask for a digital visual media item. The disclosed systems further utilize the segmentation refinement neural network to generate one or more refined segmentation masks based on uncertainly classified pixels identified from the initial segmentation mask. To illustrate, in some implementations, the disclosed systems utilize the segmentation refinement neural network to redetermine whether a set of uncertain pixels corresponds to one or more objects depicted in the digital visual media item based on low-level (e.g., local) feature values extracted from feature maps generated for the digital visual media item.