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：US10536164B2

公开(公告)日：2020-01-14

申请号：US15815883

申请日：2017-11-17

Applicant: Adobe Inc.

Inventor： Nikhil Gupta ,  Kriti Dang ,  Stakshi Jindal Garg

IPC: G06K9/36 ,  H03M7/30 ,  G06T9/20 ,  G06K9/62 ,  G06T9/00 ,  G06K9/46

Abstract: A content-creation computing system transforms an input raster graphic into a output vector graphic by applying a customization specific to visual characteristics of the input raster graphic. The content-creation computing system provides the input raster graphic to a customization-identification network having a multi-label classifier. The content-creation computing system generates, with the multi-label classifier, a first probability that a first customization operation is applicable to the input raster graphic and a second probability that a second customization operation is applicable to the input raster graphic, wherein the first probability is greater than the second probability. The content-creation computing system selects the first customization operation as the customization specific to the input raster graphic. The content-creation computing system executes a vectorization algorithm that performs the first customization operation using the input raster graphic as an input and displays or otherwise outputs a vector graphic generated by the vectorization algorithm.

公开(公告)号：US11809984B2

公开(公告)日：2023-11-07

申请号：US16192386

申请日：2018-11-15

Applicant: Adobe Inc.

Inventor： Nikhil Gupta

IPC: G06N3/08 ,  G01J3/52

CPC classification number: G06N3/08 ,  G01J3/526

Abstract: An automatic tag identification system identifies tags for color themes, a color theme referring to a set of multiple colors that work well together to create (e.g., are visually appropriate for creating) a desired effect, and a tag referring to one or more words that describe a color theme. The automatic tag identification system receives an indication of the multiple colors (e.g., five colors) for a color theme. A first machine learning system uses the indicated multiple colors to generate a color theme embedding for the color theme, which is a vector encoding or embedding of the color theme. The second machine learning system uses the color theme embedding generated by the first machine learning system to generate one or more tags that label the color theme. These one or more tags can then be saved as associated with or corresponding to the multiple colors for the color theme.

公开(公告)号：US20230127525A1

公开(公告)日：2023-04-27

申请号：US17512264

申请日：2021-10-27

Applicant: Adobe Inc.

Inventor： Nishant Rai ,  Shivam Mishra ,  Nitesh Jain ,  Nikhil Gupta ,  Anubhav Jain

IPC: G06N3/04

Abstract: The present disclosure describes methods, systems, and non-transitory computer-readable media for implementing a machine learning framework to generate a recommend digital assets from a digital image. For example, in one or more embodiments, the disclosed systems utilize a machine learning model to detect a shape, color, pattern, or other digital asset type from a digital image and then extract (and further modify) the detected asset type to create various different digital assets as recommendations. In some cases, the disclosed system utilizes the machine learning model to determine one or more digital asset classes associated with the digital image, generate preprocessed digital assets from the digital image for those digital asset classes, and generate production-ready digital assets from the preprocessed digital assets. Further, in some instances, the disclosed systems provide one or more of the digital assets via recommendations based on asset scores determined via the generation process.

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.

公开(公告)号：US20200160167A1

公开(公告)日：2020-05-21

申请号：US16192386

申请日：2018-11-15

Applicant: Adobe Inc.

Inventor： Nikhil Gupta

IPC: G06N3/08

Abstract: An automatic tag identification system identifies tags for color themes, a color theme referring to a set of multiple colors that work well together to create (e.g., are visually appropriate for creating) a desired effect, and a tag referring to one or more words that describe a color theme. The automatic tag identification system receives an indication of the multiple colors (e.g., five colors) for a color theme. A first machine learning system uses the indicated multiple colors to generate a color theme embedding for the color theme, which is a vector encoding or embedding of the color theme. The second machine learning system uses the color theme embedding generated by the first machine learning system to generate one or more tags that label the color theme. These one or more tags can then be saved as associated with or corresponding to the multiple colors for the color theme.

公开(公告)号：US10379970B2

公开(公告)日：2019-08-13

申请号：US15715670

申请日：2017-09-26

Applicant: Adobe Inc.

Inventor： Shashidhar Mangu ,  Shamit Kumar Mehta ,  Nikhil Gupta ,  Abhishek Garg

IPC: G06F11/16 ,  G06F11/00 ,  G06F3/0481

Abstract: A digital medium environment is described for automatic design discrepancy reporting of discrepancies between an actual display and its intended design. In one example, a design validation system generates a design screen model for a design screen, based on an object included in the design screen and at least one display property that defines a visual appearance of the object. The design validation system then identifies an application object that has a similar visual appearance to the defined visual appearance of the object of the design screen model. The design validation system additionally determines that a discrepancy exists between a display of the design screen model object and the application object. The design validation system also determines a value by which the at least one property of the application object is to be adjusted and outputs the value to adjust the at least one display property of the application object.