公开(公告)号：US12062119B2

公开(公告)日：2024-08-13

申请号：US17851929

申请日：2022-06-28

Applicant: ADOBE INC.

Inventor： Pranay Kumar ,  Nipun Jindal

IPC: G06T11/20 ,  G06F3/0482 ,  G06F3/04847

CPC classification number: G06T11/203 ,  G06F3/0482 ,  G06F3/04847 ,  G06T2200/24

Abstract: Embodiments presented in this disclosure provide for dynamic application of user selected visual accessibility transforms onto glyphs of standard fonts so that, for instance, a user device can present textual content to a user in a form personalized by the user to be more readable. In accordance with some aspects, a user selection of a font transformation is received. A set of initial control points of an initial glyph is transposed based on the font transformation to generate a set of modified control points. A modified glyph is constructed using differential evolution based at least on the set of initial control points and the set of modified control points.

公开(公告)号：US12210813B2

公开(公告)日：2025-01-28

申请号：US18051720

申请日：2022-11-01

Applicant: Adobe Inc.

Inventor： Pranay Kumar ,  Nipun Jindal

IPC: G06F40/109

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a multi-modal vector and identifies a recommended font corresponding to the source font based on the multi-modal vector. For instance, in one or more embodiments, the disclosed systems receive an indication of a source font and determines font embeddings and glyph metrics embedding. Furthermore, the disclosed system generates, utilizing a multi-modal font machine-learning model, a multi-modal vector representing the source font based on the font embeddings and the glyph metrics embedding.

公开(公告)号：US11886768B2

公开(公告)日：2024-01-30

申请号：US17733635

申请日：2022-04-29

Applicant: Adobe Inc.

Inventor： Pranay Kumar ,  Nipun Jindal

IPC: G06F3/16 ,  G06N3/04 ,  G06F3/04842 ,  G06F3/04883

CPC classification number: G06F3/16 ,  G06F3/04842 ,  G06F3/04883 ,  G06N3/04

Abstract: Embodiments are disclosed for real time generative audio for brush and canvas interaction in digital drawing. The method may include receiving a user input and a selection of a tool for generating audio for a digital drawing interaction. The method may further include generating intermediary audio data based on the user input and the tool selection, wherein the intermediary audio data includes a pitch and a frequency. The method may further include processing, by a trained audio transformation model and through a series of one or more layers of the trained audio transformation model, the intermediary audio data. The method may further include adjusting the series of one or more layers of the trained audio transformation model to include one or more additional layers to produce an adjusted audio transformation model. The method may further include generating, by the adjusted audio transformation model, an audio sample based on the intermediary audio data.

公开(公告)号：US20240143897A1

公开(公告)日：2024-05-02

申请号：US18051720

申请日：2022-11-01

Applicant: Adobe Inc.

Inventor： Pranay Kumar ,  Nipun Jindal

IPC: G06F40/109

CPC classification number: G06F40/109

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a multi-modal vector and identifies a recommended font corresponding to the source font based on the multi-modal vector. For instance, in one or more embodiments, the disclosed systems receive an indication of a source font and determines font embeddings and glyph metrics embedding. Furthermore, the disclosed system generates, utilizing a multi-modal font machine-learning model, a multi-modal vector representing the source font based on the font embeddings and the glyph metrics embedding.