Patents by Inventor Théo CHARVET

Théo CHARVET 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).

  • SYSTEMS AND METHODS FOR MACHINE LEARNED IMAGE CONVERSION
    Publication number: 20230360174
    Abstract: A computer system is provided for converting images through use of a trained neural network. A source image is divided into blocks and context data is added to each pixel block. The context blocks are split into channels and each channel from the same context block is added to the same activation matrix. The action matrix is then executed against a trained neural network to produce a changed activation matrix. The changed activation matrix is then used to generate a converted image.
    Type: Application
    Filed: July 13, 2023
    Publication date: November 9, 2023
    Inventors: Alexandre DELATTRE, Théo CHARVET, Raphaël PONCET
  • Systems and methods for machine learned image conversion
    Patent number: 11748848
    Abstract: A computer system is provided for converting images through use of a trained neural network. A source image is divided into blocks and context data is added to each pixel block. The context blocks are split into channels and each channel from the same context block is added to the same activation matrix. The action matrix is then executed against a trained neural network to produce a changed activation matrix. The changed activation matrix is then used to generate a converted image.
    Type: Grant
    Filed: June 21, 2022
    Date of Patent: September 5, 2023
    Assignee: NINTENDO CO., LTD.
    Inventors: Alexandre Delattre, Théo Charvet, Raphaël Poncet
  • Systems and methods for machine learned image conversion
    Patent number: 11494875
    Abstract: A computer system is provided for converting images through use of a trained neural network. A source image is divided into blocks and context data is added to each pixel block. The context blocks are split into channels and each channel from the same context block is added to the same activation matrix. The action matrix is then executed against a trained neural network to produce a changed activation matrix. The changed activation matrix is then used to generate a converted image.
    Type: Grant
    Filed: March 25, 2020
    Date of Patent: November 8, 2022
    Assignee: NINTENDO CO., LTD.
    Inventors: Alexandre Delattre, Théo Charvet
  • SYSTEMS AND METHODS FOR MACHINE LEARNED IMAGE CONVERSION
    Publication number: 20220335570
    Abstract: A computer system is provided for converting images through use of a trained neural network. A source image is divided into blocks and context data is added to each pixel block. The context blocks are split into channels and each channel from the same context block is added to the same activation matrix. The action matrix is then executed against a trained neural network to produce a changed activation matrix. The changed activation matrix is then used to generate a converted image.
    Type: Application
    Filed: June 21, 2022
    Publication date: October 20, 2022
    Inventors: Alexandre DELATTRE, Théo Charvet, Raphaël Poncet
  • Systems and methods for machine learned image conversion
    Patent number: 11379951
    Abstract: A computer system is provided for converting images through use of a trained neural network. A source image is divided into blocks and context data is added to each pixel block. The context blocks are split into channels and each channel from the same context block is added to the same activation matrix. The action matrix is then executed against a trained neural network to produce a changed activation matrix. The changed activation matrix is then used to generate a converted image.
    Type: Grant
    Filed: March 25, 2020
    Date of Patent: July 5, 2022
    Assignee: NINTENDO CO., LTD.
    Inventors: Alexandre Delattre, Théo Charvet, Raphaël Poncet
  • SYSTEMS AND METHODS FOR MACHINE LEARNED IMAGE CONVERSION
    Publication number: 20210304356
    Abstract: A computer system is provided for converting images through use of a trained neural network. A source image is divided into blocks and context data is added to each pixel block. The context blocks are split into channels and each channel from the same context block is added to the same activation matrix. The action matrix is then executed against a trained neural network to produce a changed activation matrix. The changed activation matrix is then used to generate a converted image.
    Type: Application
    Filed: March 25, 2020
    Publication date: September 30, 2021
    Inventors: Alexandre DELATTRE, Théo CHARVET, Raphaël PONCET
  • SYSTEMS AND METHODS FOR MACHINE LEARNED IMAGE CONVERSION
    Publication number: 20210304355
    Abstract: A computer system is provided for converting images through use of a trained neural network. A source image is divided into blocks and context data is added to each pixel block. The context blocks are split into channels and each channel from the same context block is added to the same activation matrix. The action matrix is then executed against a trained neural network to produce a changed activation matrix. The changed activation matrix is then used to generate a converted image.
    Type: Application
    Filed: March 25, 2020
    Publication date: September 30, 2021
    Inventors: Alexandre DELATTRE, Théo CHARVET