公开(公告)号：US20240289965A1

公开(公告)日：2024-08-29

申请号：US18176230

申请日：2023-02-28

Applicant: Adobe Inc.

Inventor： Praveen Gelra ,  Ashish Anand ,  Ansh Gupta ,  Ajay Bedi

IPC: G06T7/194 ,  G06T3/40

CPC classification number: G06T7/194 ,  G06T3/4046 ,  G06T2207/20084

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate a modified digital image depicting a transparent object utilizing a transparency properties neural network. For example, the disclosed system accesses a trimap for a source digital image depicting a transparent object. The disclosed system utilizes the trimap of the source digital image and the source digital image to generate an alpha matte and a refractive flow. Specifically, the disclosed system generates the alpha matte and refractive flow by utilizing a transparency properties neural network. Furthermore, the disclosed system generates the modified digital image depicting the transparent object (from the source digital image) within a background of a target digital image, by modifying a portion of the background of a target digital image behind the transparent object utilizing the alpha matte and the refractive flow.

公开(公告)号：US11087515B2

公开(公告)日：2021-08-10

申请号：US16682936

申请日：2019-11-13

Applicant: Adobe Inc.

Inventor： William Eisley ,  Sandeep Pradhan ,  Robert Sargent ,  Puneet Gupta ,  Paul George ,  Harjot Singh ,  Frank Stokes-Guinan ,  Ashish Anand ,  Abhishek Garg

IPC: G06T11/60 ,  G06T1/00

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for losslessly exchanging image layer data between image applications by generating an edit-restricted layer for one image application to represent an incompatible or unsupported image layer from another image application. For example, the disclosed system can determine that one or more image layers in a layered image file formatted for a layered image application include characteristics incompatible (e.g., unsupported) with a feature-restricted image application. The disclosed system can then generate an edit-restricted image layer representing the image layer(s) in the feature-restricted image application by limiting or preventing edit operations to the edit-restricted layer as a type of preview object. The disclosed system can also store image layer data from the feature-restricted image application back to the layered image file for viewing and editing in the layered image application without loss of image layer data corresponding to the edit-restricted layer.

公开(公告)号：US20200081691A1

公开(公告)日：2020-03-12

申请号：US16126849

申请日：2018-09-10

Applicant: Adobe Inc.

Inventor： Nikhil Gupta ,  Shivam Mishra ,  Ashish Anand ,  Arpit Kumar Singh

IPC: G06F8/38 ,  G06N3/04 ,  G06F9/448 ,  G06F3/0484

Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that use a design-component-neural network to categorize a design component from an interface-design file as a platform widget corresponding to a particular computing platform. Having categorized the design component as a platform widget, in certain implementations, the disclosed systems compare and validate properties of the design component against user-interface guidelines for the particular computing platform. Upon determining that the design component does not comply with a user-interface guideline, the systems can provide and implement options to modify the design component to comply with the user-interface guideline.

公开(公告)号：US11093130B1

公开(公告)日：2021-08-17

申请号：US16822826

申请日：2020-03-18

Applicant: Adobe Inc.

Inventor： Deep Sinha ,  Ashish Anand

IPC: G06F3/0488 ,  G06T11/20 ,  G06T11/00 ,  G06F16/51

Abstract: Techniques and systems are provided for performing drawing tool identification and retrieval. For instance, based on a user creating content within a digital image using a drawing tool, a drawing tool-retrieval system may determine a unique identifier corresponding to the drawing tool. The identifier may indicate the type of the drawing tool, as well as any configurable settings of the drawing tool selected by the user. The drawing tool-retrieval system can store the identifier in association with pixels corresponding to the content. When the user wishes to use the drawing tool again, the user can provide a drawing tool-picking input that includes selection of a pixel corresponding to the content. In response to the drawing tool-picking input, the drawing tool-retrieval system can obtain the identifier of the drawing tool and then activate the drawing tool to enable the user to edit the image with the drawing tool.

公开(公告)号：US20210142541A1

公开(公告)日：2021-05-13

申请号：US16682936

申请日：2019-11-13

Applicant: Adobe Inc.

Inventor： William Eisley ,  Sandeep Pradhan ,  Robert Sargent ,  Puneet Gupta ,  Paul George ,  Harjot Singh ,  Frank Stokes-Guinan ,  Ashish Anand ,  Abhishek Garg

IPC: G06T11/60 ,  G06T1/00

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for losslessly exchanging image layer data between image applications by generating an edit-restricted layer for one image application to represent an incompatible or unsupported image layer from another image application. For example, the disclosed system can determine that one or more image layers in a layered image file formatted for a layered image application include characteristics incompatible (e.g., unsupported) with a feature-restricted image application. The disclosed system can then generate an edit-restricted image layer representing the image layer(s) in the feature-restricted image application by limiting or preventing edit operations to the edit-restricted layer as a type of preview object. The disclosed system can also store image layer data from the feature-restricted image application back to the layered image file for viewing and editing in the layered image application without loss of image layer data corresponding to the edit-restricted layer.

公开(公告)号：US10732942B2

公开(公告)日：2020-08-04

申请号：US16126849

申请日：2018-09-10

Applicant: Adobe Inc.

Inventor： Nikhil Gupta ,  Shivam Mishra ,  Ashish Anand ,  Arpit Kumar Singh

IPC: G06F9/44 ,  G06F8/38 ,  G06F3/0484 ,  G06F9/448 ,  G06N3/04

Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that use a design-component-neural network to categorize a design component from an interface-design file as a platform widget corresponding to a particular computing platform. Having categorized the design component as a platform widget, in certain implementations, the disclosed systems compare and validate properties of the design component against user-interface guidelines for the particular computing platform. Upon determining that the design component does not comply with a user-interface guideline, the systems can provide and implement options to modify the design component to comply with the user-interface guideline.