Patents by Inventor EUNBYUNG PARK

EUNBYUNG PARK has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Generating novel views of a three-dimensional object based on a single two-dimensional image
    Patent number: 11115645
    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.
    Type: Grant
    Filed: December 21, 2018
    Date of Patent: September 7, 2021
    Assignee: ADOBE INC.
    Inventors: Jimei Yang, Duygu Ceylan Aksit, Mehmet Ersin Yumer, Eunbyung Park
  • GENERATING NOVEL VIEWS OF A THREE-DIMENSIONAL OBJECT BASED ON A SINGLE TWO-DIMENSIONAL IMAGE
    Publication number: 20190124322
    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.
    Type: Application
    Filed: December 21, 2018
    Publication date: April 25, 2019
    Inventors: JIMEI YANG, DUYGU CEYLAN AKSIT, MEHMET ERSIN YUMER, EUNBYUNG PARK
  • Generating novel views of a three-dimensional object based on a single two-dimensional image
    Patent number: 10165259
    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.
    Type: Grant
    Filed: February 15, 2017
    Date of Patent: December 25, 2018
    Assignee: Adobe Systems Incorporated
    Inventors: Jimei Yang, Duygu Ceylan Aksit, Mehmet Ersin Yumer, Eunbyung Park
  • GENERATING NOVEL VIEWS OF A THREE-DIMENSIONAL OBJECT BASED ON A SINGLE TWO-DIMENSIONAL IMAGE
    Publication number: 20180234671
    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.
    Type: Application
    Filed: February 15, 2017
    Publication date: August 16, 2018
    Inventors: JIMEI YANG, DUYGU CEYLAN AKSIT, MEHMET ERSIN YUMER, EUNBYUNG PARK