中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

22 records (took 0.018 seconds)

    Procedural modeling using autoencoder neural networks
    1.
    发明授权
    Procedural modeling using autoencoder neural networks 有权

    公开(公告)号：US10552730B2

    公开(公告)日：2020-02-04

    申请号：US14788178

    申请日：2015-06-30

    Applicant: ADOBE INC.

    Inventor： Mehmet Ersin Yumer ,  Radomir Mech ,  Paul John Asente ,  Gavin Stuart Peter Miller

    IPC: G06N3/04

    Abstract: An intuitive object-generation experience is provided by employing an autoencoder neural network to reduce the dimensionality of a procedural model. A set of sample objects are generated using the procedural model. In embodiments, the sample objects may be selected according to visual features such that the sample objects are uniformly distributed in visual appearance. Both procedural model parameters and visual features from the sample objects are used to train an autoencoder neural network, which maps a small number of new parameters to the larger number of procedural model parameters of the original procedural model. A user interface may be provided that allows users to generate new objects by adjusting the new parameters of the trained autoencoder neural network, which outputs procedural model parameters. The output procedural model parameters may be provided to the procedural model to generate the new objects.

    Dynamic path modification and extension
    2.
    发明授权
    Dynamic path modification and extension 有权

    公开(公告)号：US10339679B2

    公开(公告)日：2019-07-02

    申请号：US15055118

    申请日：2016-02-26

    Applicant: Adobe Inc.

    Inventor： Mehmet Ersin Yumer

    IPC: G06T11/20 ,  G06F3/0484 ,  G06F3/0488 ,  G06F17/17

    Abstract: A digital medium environment is described to dynamically modify or extend an existing path in a user interface. An un-parameterized input is received that is originated by user interaction with a user interface to specify a path to be drawn. A parameterized path is fit as a mathematical ordering representation of the path to be drawn as specified by the un-parametrized input. A determination is made as to whether the parameterized path is to extend or modify the existing path in the user interface. The existing path is modified or extended in the user interface using the parameterized path in response to the determining that the parameterized path is to modify or extend the existing path.

    Generating novel views of a three-dimensional object based on a single two-dimensional image
    4.
    发明授权
    Generating novel views of a three-dimensional object based on a single two-dimensional image 有权

    公开(公告)号：US11115645B2

    公开(公告)日：2021-09-07

    申请号：US16230872

    申请日：2018-12-21

    Applicant: ADOBE INC.

    Inventor： Jimei Yang ,  Duygu Ceylan Aksit ,  Mehmet Ersin Yumer ,  Eunbyung Park

    IPC: G06K9/00 ,  H04N13/282 ,  G06K9/62 ,  H04N13/161 ,  H04N13/275 ,  G06T11/00 ,  G06T15/20 ,  H04N13/111

    Abstract: Embodiments are directed towards providing a target view, from a target viewpoint, of a 3D object. A source image, from a source viewpoint and including a common portion of the object, is encoded in 2D data. An intermediate image that includes an intermediate view of the object is generated based on the data. The intermediate view is from the target viewpoint and includes the common portion of the object and a disoccluded portion of the object not visible in the source image. The intermediate image includes a common region and a disoccluded region corresponding to the disoccluded portion of the object. The disoccluded region is updated to include a visual representation of a prediction of the disoccluded portion of the object. The prediction is based on a trained image completion model. The target view is based on the common region and the updated disoccluded region of the intermediate image.

    Dynamic path modification and extension
    5.
    发明授权
    Dynamic path modification and extension 有权

    公开(公告)号：US11049296B2

    公开(公告)日：2021-06-29

    申请号：US16428436

    申请日：2019-05-31

    Applicant: Adobe Inc.

    Inventor： Mehmet Ersin Yumer

    IPC: G06T11/20 ,  G06F3/0484 ,  G06F17/17 ,  G06F3/0488

    Abstract: A digital medium environment is described to dynamically modify or extend an existing path in a user interface. An un-parameterized input is received that is originated by user interaction with a user interface to specify a path to be drawn. A parameterized path is fit as a mathematical ordering representation of the path to be drawn as specified by the un-parametrized input. A determination is made as to whether the parameterized path is to extend or modify the existing path in the user interface. The existing path is modified or extended in the user interface using the parameterized path in response to the determining that the parameterized path is to modify or extend the existing path.

    Drawing Curves in Space Guided by 3-D Objects
    6.
    发明申请
    Drawing Curves in Space Guided by 3-D Objects 审中-公开

    公开(公告)号：US20200250865A1

    公开(公告)日：2020-08-06

    申请号：US16855328

    申请日：2020-04-22

    Applicant: Adobe Inc.

    Inventor： Vojtech Krs ,  Radomir Mech ,  Nathan Aaron Carr ,  Mehmet Ersin Yumer

    IPC: G06T11/20 ,  G06F17/00

    Abstract: Various embodiments enable curves to be drawn around 3-D objects by intelligently determining or inferring how the curve flows in the space around the outside of the 3-D object. The various embodiments enable such curves to be drawn without having to constantly rotate the 3-D object. In at least some embodiments, curve flow is inferred by employing a vertex position discovery process, a path discovery process, and a final curve construction process.

    Drawing curves in space guided by 3-D objects
    7.
    发明授权
    Drawing curves in space guided by 3-D objects 有权

    公开(公告)号：US10657682B2

    公开(公告)日：2020-05-19

    申请号：US15485980

    申请日：2017-04-12

    Applicant: Adobe Inc.

    Inventor： Vojtech Krs ,  Radomir Mech ,  Nathan Aaron Carr ,  Mehmet Ersin Yumer

    IPC: G06T11/20 ,  G06F17/00

    Abstract: Various embodiments enable curves to be drawn around 3-D objects by intelligently determining or inferring how the curve flows in the space around the outside of the 3-D object. The various embodiments enable such curves to be drawn without having to constantly rotate the 3-D object. In at least some embodiments, curve flow is inferred by employing a vertex position discovery process, a path discovery process, and a final curve construction process.

    Drawing curves in space guided by 3-D objects
    10.
    发明授权
    Drawing curves in space guided by 3-D objects 有权

    公开(公告)号：US11069099B2

    公开(公告)日：2021-07-20

    申请号：US16855328

    申请日：2020-04-22

    Applicant: Adobe Inc.

    Inventor： Vojtech Krs ,  Radomir Mech ,  Nathan Aaron Carr ,  Mehmet Ersin Yumer

    IPC: G06T11/20 ,  G06F17/00

    Abstract: Various embodiments enable curves to be drawn around 3-D objects by intelligently determining or inferring how the curve flows in the space around the outside of the 3-D object. The various embodiments enable such curves to be drawn without having to constantly rotate the 3-D object. In at least some embodiments, curve flow is inferred by employing a vertex position discovery process, a path discovery process, and a final curve construction process.

Patent Agency Ranking