中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.012 seconds)

    Automatic generation of context-aware composite images
    1.
    发明授权
    Automatic generation of context-aware composite images 有权

    公开(公告)号：US11158100B2

    公开(公告)日：2021-10-26

    申请号：US16275261

    申请日：2019-02-13

    Applicant: ADOBE INC.

    Inventor： Kumar Ayush ,  Harsh Vardhan Chopra

    IPC: G06T11/60 ,  G06T11/00 ,  G06T7/90 ,  G06T7/70 ,  G06K9/62

    Abstract: The present invention enables the automatic generation and recommendation of embedded images. An embedded image includes a visual representation of a context-appropriate object embedded within a scene image. The context and aesthetic properties (e.g., the colors, textures, lighting, position, orientation, and size) of the visual representation of the object may be automatically varied to increase an associated objective compatibility score that is based on the context and aesthetics of the scene image. The scene image may depict a visual representation of a scene, e.g., a background scene. Thus, a scene image may be a background image that depicts a background and/or scene to automatically pair with the object. The object may be a three-dimensional (3D) physical or virtual object. The automatically generated embedded image may be a composite image that includes at least a partially optimized visual representation of a context-appropriate object composited within the scene image.

    AUTOMATIC GENERATION OF CONTEXT-AWARE COMPOSITE IMAGES
    3.
    发明申请
    AUTOMATIC GENERATION OF CONTEXT-AWARE COMPOSITE IMAGES 审中-公开

    公开(公告)号：US20200258276A1

    公开(公告)日：2020-08-13

    申请号：US16275261

    申请日：2019-02-13

    Applicant: ADOBE INC.

    Inventor： Kumar Ayush ,  Harsh Vardhan Chopra

    IPC: G06T11/60 ,  G06T7/90 ,  G06K9/62 ,  G06T7/70 ,  G06T11/00

    Abstract: The present invention enables the automatic generation and recommendation of embedded images. An embedded image includes a visual representation of a context-appropriate object embedded within a scene image. The context and aesthetic properties (e.g., the colors, textures, lighting, position, orientation, and size) of the visual representation of the object may be automatically varied to increase an associated objective compatibility score that is based on the context and aesthetics of the scene image. The scene image may depict a visual representation of a scene, e.g., a background scene. Thus, a scene image may be a background image that depicts a background and/or scene to automatically pair with the object. The object may be a three-dimensional (3D) physical or virtual object. The automatically generated embedded image may be a composite image that includes at least a partially optimized visual representation of a context-appropriate object composited within the scene image.

    Generating views of three-dimensional models illustrating defects
    4.
    发明授权
    Generating views of three-dimensional models illustrating defects 有权

    公开(公告)号：US10410410B2

    公开(公告)日：2019-09-10

    申请号：US15948528

    申请日：2018-04-09

    Applicant: Adobe Inc.

    Inventor： Naveen Goel ,  Mayur Hemani ,  Harsh Vardhan Chopra ,  Amit Mittal

    IPC: G06T17/00 ,  G06T15/04 ,  G06T15/06 ,  G06K9/62 ,  G06T15/20 ,  G06K9/00 ,  G06K9/46

    Abstract: Systems and methods are disclosed for generating viewpoints and/or digital images of defects in a three-dimensional model. In particular, in one or more embodiments, the disclosed systems and methods generate exterior viewpoints by clustering intersection points between a bounding sphere and rays originating from exterior vertices corresponding to one or more defects. In addition, in one or more embodiments, the disclosed systems and methods generate interior viewpoints by clustering intersection points between one or more medial spheres and rays originating from vertices corresponding to interior vertices corresponding to one or more defects. Furthermore, the disclosed systems and methods can apply colors to vertices corresponding to defects in the three-dimensional model such that adjacent vertices in the three-dimensional model have different colors and are more readily discernable.

Patent Agency Ranking