公开(公告)号：US20240312085A1

公开(公告)日：2024-09-19

申请号：US18121454

申请日：2023-03-14

Applicant: Adobe Inc.

Inventor： Ashish Jain ,  Avil Aneja

IPC: G06T11/40 ,  G06V30/18 ,  G06V30/32

CPC classification number: G06T11/40 ,  G06V30/18105 ,  G06V30/347

Abstract: Reference based digital content stylization techniques are described that enable generation of stylized digital content from a plain text input based on visual style attributes of reference digital content. A content processing system, for instance, receives input digital content including text and reference digital content with a particular visual style. The content processing system determines visual style attributes of the reference digital content, such as a text size, color, font, etc. The content processing system generates an input content classification scheme that includes semantic structure identifiers to classify text of the input digital content, e.g., as a header, subheader, paragraph, and so forth. Based on the input content classification scheme, the content processing system generates stylized digital content by applying the visual style attributes of the reference digital content to the text of the input digital content.

公开(公告)号：US20240273281A1

公开(公告)日：2024-08-15

申请号：US18107772

申请日：2023-02-09

Applicant: Adobe Inc.

Inventor： Ashish Jain ,  Avil Aneja

IPC: G06F40/117 ,  G06F40/106

CPC classification number: G06F40/117 ,  G06F16/957 ,  G06F40/106 ,  G06F3/0482

Abstract: Certain aspects and features of the present disclosure involve receiving theme-based input corresponding to a first document and generating document tags corresponding to the first document based on the theme-based input. The aspects and features further involve generating, using the document tags, a coefficient of similarity between the first document and library documents, and producing candidate documents from the library documents by comparing the coefficient of similarity for each of a number of library documents to a threshold. The aspects and features additionally involve selecting a second document from among the candidate documents and transferring at least one style from the second document to the first document based on an object similarity score corresponding to an object of a plurality of objects in the second document.