Patents by Inventor Joshua Tenenbaum

Joshua Tenenbaum 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 reconstructing a scene in three dimensions from a two-dimensional image
    Patent number: 11887248
    Abstract: Systems and methods described herein relate to reconstructing a scene in three dimensions from a two-dimensional image. One embodiment processes an image using a detection transformer to detect an object in the scene and to generate a NOCS map of the object and a background depth map; uses MLPs to relate the object to a differentiable database of object priors (PriorDB); recovers, from the NOCS map, a partial 3D object shape; estimates an initial object pose; fits a PriorDB object prior to align in geometry and appearance with the partial 3D shape to produce a complete shape and refines the initial pose estimate; generates an editable and re-renderable 3D scene reconstruction based, at least in part, on the complete shape, the refined pose estimate, and the depth map; and controls the operation of a robot based, at least in part, on the editable and re-renderable 3D scene reconstruction.
    Type: Grant
    Filed: March 16, 2022
    Date of Patent: January 30, 2024
    Assignees: Toyota Research Institute, Inc., Massachusetts Institute of Technology, The Board of Trustees of the Leland Standford Junior Univeristy
    Inventors: Sergey Zakharov, Wadim Kehl, Vitor Guizilini, Adrien David Gaidon, Rares A. Ambrus, Dennis Park, Joshua Tenenbaum, Jiajun Wu, Fredo Durand, Vincent Sitzmann
  • SYSTEMS AND METHODS FOR RECONSTRUCTING A SCENE IN THREE DIMENSIONS FROM A TWO-DIMENSIONAL IMAGE
    Publication number: 20220414974
    Abstract: Systems and methods described herein relate to reconstructing a scene in three dimensions from a two-dimensional image. One embodiment processes an image using a detection transformer to detect an object in the scene and to generate a NOCS map of the object and a background depth map; uses MLPs to relate the object to a differentiable database of object priors (PriorDB); recovers, from the NOCS map, a partial 3D object shape; estimates an initial object pose; fits a PriorDB object prior to align in geometry and appearance with the partial 3D shape to produce a complete shape and refines the initial pose estimate; generates an editable and re-renderable 3D scene reconstruction based, at least in part, on the complete shape, the refined pose estimate, and the depth map; and controls the operation of a robot based, at least in part, on the editable and re-renderable 3D scene reconstruction.
    Type: Application
    Filed: March 16, 2022
    Publication date: December 29, 2022
    Applicants: Toyota Research Institute, Inc., Massachusetts Institute of Technology, The Board of Trustees of the Leland Stanford Junior University
    Inventors: Sergey Zakharov, Wadim Kehl, Vitor Guizilini, Adrien David Gaidon, Rares A. Ambrus, Dennis Park, Joshua Tenenbaum, Jiajun Wu, Fredo Durand, Vincent Sitzmann