Patents by Inventor Jeroen SCHULTE

Jeroen SCHULTE 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).

  • Deep SDR-HDR Conversion
    Publication number: 20240013354
    Abstract: The exemplary embodiments relate to converting Standard Dynamic Range (SDR) content to High Dynamic Range (HDR) content using a machine learning system. In some embodiments, the neural network is trained to convert an input SDR image into an HDR image using the encoded representation of a training SDR image and a training HDR image. In other embodiments, the neural network is trained to convert an input SDR image into an HDR image using a predefined set of color grading actions and the training images.
    Type: Application
    Filed: September 25, 2023
    Publication date: January 11, 2024
    Inventors: Tunc Ozan Aydin, Yang Zhang, Blake Sloan, Jeroen Schulte, Michael Maloney
  • Deep SDR-HDR conversion
    Patent number: 11803946
    Abstract: The exemplary embodiments relate to converting Standard Dynamic Range (SDR) content to High Dynamic Range (HDR) content using a machine learning system. In some embodiments, the neural network is trained to convert an input SDR image into an HDR image using the encoded representation of a training SDR image and a training HDR image. In other embodiments, the neural network is trained to convert an input SDR image into an HDR image using a predefined set of color grading actions and the training images.
    Type: Grant
    Filed: September 14, 2020
    Date of Patent: October 31, 2023
    Assignee: Disney Enterprises, Inc.
    Inventors: Tunc Ozan Aydin, Yang Zhang, Blake Sloan, Jeroen Schulte, Michael Maloney
  • Deep SDR-HDR Conversion
    Publication number: 20220084170
    Abstract: The exemplary embodiments relate to converting Standard Dynamic Range (SDR) content to High Dynamic Range (HDR) content using a machine learning system. In some embodiments, the neural network is trained to convert an input SDR image into an HDR image using the encoded representation of a training SDR image and a training HDR image. In other embodiments, the neural network is trained to convert an input SDR image into an HDR image using a predefined set of color grading actions and the training images.
    Type: Application
    Filed: September 14, 2020
    Publication date: March 17, 2022
    Inventors: Tunc Ozan AYDIN, Yang ZHANG, Blake SLOAN, Jeroen SCHULTE, Michael MALONEY