Patents by Inventor Heiko Strathmann

Heiko Strathmann 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).

  • Persistent message passing for graph neural networks
    Patent number: 12417373
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing persistent message passing using graph neural networks.
    Type: Grant
    Filed: May 31, 2022
    Date of Patent: September 16, 2025
    Assignee: DeepMind Technologies Limited
    Inventors: Heiko Strathmann, Mohammadamin Barekatain, Charles Blundell, Petar Velickovic
  • RENDERING NEW IMAGES OF SCENES USING GEOMETRY-AWARE NEURAL NETWORKS CONDITIONED ON LATENT VARIABLES
    Publication number: 20240070972
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for rendering a new image that depicts a scene from a perspective of a camera at a new camera location. In one aspect, a method comprises: receiving a plurality of observations characterizing the scene; generating a latent variable representing the scene from the plurality of observations characterizing the scene; conditioning a scene representation neural network on the latent variable representing the scene, wherein the scene representation neural network conditioned on the latent variable representing the scene defines a geometric model of the scene as a three-dimensional (3D) radiance field; and rendering the new image that depicts the scene from the perspective of the camera at the new camera location using the scene representation neural network conditioned on the latent variable representing the scene.
    Type: Application
    Filed: February 4, 2022
    Publication date: February 29, 2024
    Inventors: Adam Roman Kosiorek, Heiko Strathmann, Danilo Jimenez Rezende, Daniel Zoran, Pol Moreno Comellas
  • PERSISTENT MESSAGE PASSING FOR GRAPH NEURAL NETWORKS
    Publication number: 20220383074
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing persistent message passing using graph neural networks.
    Type: Application
    Filed: May 31, 2022
    Publication date: December 1, 2022
    Inventors: Heiko Strathmann, Mohammadamin Barekatain, Charles Blundell, Petar Velickovic