Patents by Inventor Matthew R. Walter

Matthew R. Walter 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).

  • Publication number: 20240029286
    Abstract: A method of generating additional supervision data to improve learning of a geometrically-consistent latent scene representation with a geometric scene representation architecture is provided. The method includes receiving, with a computing device, a latent scene representation encoding a pointcloud from images of a scene captured by a plurality of cameras each with known intrinsics and poses, generating a virtual camera having a viewpoint different from viewpoints of the plurality of cameras, projecting information from the pointcloud onto the viewpoint of the virtual camera, and decoding the latent scene representation based on the virtual camera thereby generating an RGB image and depth map corresponding to the viewpoint of the virtual camera for implementation as additional supervision data.
    Type: Application
    Filed: February 16, 2023
    Publication date: January 25, 2024
    Applicants: Toyota Research Institute, Inc., Toyota Jidosha Kabushiki Kaisha, Toyota Technological Institute at Chicago
    Inventors: Vitor Guizilini, Igor Vasiljevic, Adrien D. Gaidon, Jiading Fang, Gregory Shakhnarovich, Matthew R. Walter, Rares A. Ambrus
  • Publication number: 20230080638
    Abstract: Systems and methods described herein relate to self-supervised learning of camera intrinsic parameters from a sequence of images. One embodiment produces a depth map from a current image frame captured by a camera; generates a point cloud from the depth map using a differentiable unprojection operation; produces a camera pose estimate from the current image frame and a context image frame; produces a warped point cloud based on the camera pose estimate; generates a warped image frame from the warped point cloud using a differentiable projection operation; compares the warped image frame with the context image frame to produce a self-supervised photometric loss; updates a set of estimated camera intrinsic parameters on a per-image-sequence basis using one or more gradients from the self-supervised photometric loss; and generates, based on a converged set of learned camera intrinsic parameters, a rectified image frame from an image frame captured by the camera.
    Type: Application
    Filed: March 11, 2022
    Publication date: March 16, 2023
    Applicants: Toyota Research Institute, Inc., Toyota Technological Institute at Chicago
    Inventors: Vitor Guizilini, Adrien David Gaidon, Rares A. Ambrus, Igor Vasiljevic, Jiading Fang, Gregory Shakhnarovich, Matthew R. Walter