Patents by Inventor Boyang Deng

Boyang Deng 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).

  • Convex representation of objects using neural network
    Patent number: 11978268
    Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.
    Type: Grant
    Filed: November 18, 2022
    Date of Patent: May 7, 2024
    Assignee: Google LLC
    Inventors: Boyang Deng, Kyle Genova, Soroosh Yazdani, Sofien Bouaziz, Geoffrey E. Hinton, Andrea Tagliasacchi
  • CONVEX REPRESENTATION OF OBJECTS USING NEURAL NETWORK
    Publication number: 20230078756
    Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.
    Type: Application
    Filed: November 18, 2022
    Publication date: March 16, 2023
    Inventors: Boyang Deng, Kyle Genova, Soroosh Yazdani, Sofien Bouaziz, Geoffrey E. Hinton, Andrea Tagliasacchi
  • Convex representation of objects using neural network
    Patent number: 11508167
    Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.
    Type: Grant
    Filed: April 13, 2020
    Date of Patent: November 22, 2022
    Assignee: Google LLC
    Inventors: Boyang Deng, Kyle Genova, Soroosh Yazdani, Sofien Bouaziz, Geoffrey E. Hinton, Andrea Tagliasacchi
  • Convex Representation of Objects Using Neural Network
    Publication number: 20210319209
    Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.
    Type: Application
    Filed: April 13, 2020
    Publication date: October 14, 2021
    Inventors: Boyang Deng, Kyle Genova, Soroosh Yazdani, Sofien Bouaziz, Geoffrey E. Hinton, Andrea Tagliasacchi