Patents by Inventor THOMAS KISER

THOMAS KISER 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).

  • Generating animated three-dimensional models from captured images
    Patent number: 11068698
    Abstract: A three-dimensional model (e.g., motion capture model) of a user is generated from captured images or captured video of the user. A machine learning network may track poses and expressions of the user to generate and refine the three-dimensional model. Refinement of the three-dimensional model may provide more accurate tracking of the user's face. Refining of the three-dimensional model may include refining the determinations of poses and expressions at defined locations (e.g., eye corners and/or nose) in the three-dimensional model. The refining may occur in an iterative process. Tracking of the three-dimensional model over time (e.g., during video capture) may be used to generate an animated three-dimensional model (e.g., an animated puppet) of the user that simulates the user's poses and expressions.
    Type: Grant
    Filed: September 27, 2019
    Date of Patent: July 20, 2021
    Assignee: Apple Inc.
    Inventors: Sofien Bouaziz, Brian Amberg, Thibaut Weise, Patrick Snape, Stefan Brugger, Alex Mansfield, Reinhard Knothe, Thomas Kiser
  • GENERATING ANIMATED THREE-DIMENSIONAL MODELS FROM CAPTURED IMAGES
    Publication number: 20200125835
    Abstract: A three-dimensional model (e.g., motion capture model) of a user is generated from captured images or captured video of the user. A machine learning network may track poses and expressions of the user to generate and refine the three-dimensional model. Refinement of the three-dimensional model may provide more accurate tracking of the user's face. Refining of the three-dimensional model may include refining the determinations of poses and expressions at defined locations (e.g., eye corners and/or nose) in the three-dimensional model. The refining may occur in an iterative process. Tracking of the three-dimensional model over time (e.g., during video capture) may be used to generate an animated three-dimensional model (e.g., an animated puppet) of the user that simulates the user's poses and expressions.
    Type: Application
    Filed: September 27, 2019
    Publication date: April 23, 2020
    Applicant: Apple Inc.
    Inventors: Sofien Bouaziz, Brian Amberg, Thibaut Weise, Patrick Snape, Stefan Brugger, Alex Mansfield, Reinhard Knothe, Thomas Kiser
  • Generating animated three-dimensional models from captured images
    Patent number: 10430642
    Abstract: A three-dimensional model (e.g., motion capture model) of a user is generated from captured images or captured video of the user. A machine learning network may track poses and expressions of the user to generate and refine the three-dimensional model. Refinement of the three-dimensional model may provide more accurate tracking of the user's face. Refining of the three-dimensional model may include refining the determinations of poses and expressions at defined locations (e.g., eye corners and/or nose) in the three-dimensional model. The refining may occur in an iterative process. Tracking of the three-dimensional model over time (e.g., during video capture) may be used to generate an animated three-dimensional model (e.g., an animated puppet) of the user that simulates the user's poses and expressions.
    Type: Grant
    Filed: March 23, 2018
    Date of Patent: October 1, 2019
    Assignee: Apple Inc.
    Inventors: Sofien Bouaziz, Brian Amberg, Thibaut Weise, Patrick Snape, Stefan Brugger, Alex Mansfield, Reinhard Knothe, Thomas Kiser
  • GENERATING ANIMATED THREE-DIMENSIONAL MODELS FROM CAPTURED IMAGES
    Publication number: 20190180084
    Abstract: A three-dimensional model (e.g., motion capture model) of a user is generated from captured images or captured video of the user. A machine learning network may track poses and expressions of the user to generate and refine the three-dimensional model. Refinement of the three-dimensional model may provide more accurate tracking of the user's face. Refining of the three-dimensional model may include refining the determinations of poses and expressions at defined locations (e.g., eye corners and/or nose) in the three-dimensional model. The refining may occur in an iterative process. Tracking of the three-dimensional model over time (e.g., during video capture) may be used to generate an animated three-dimensional model (e.g., an animated puppet) of the user that simulates the user's poses and expressions.
    Type: Application
    Filed: March 23, 2018
    Publication date: June 13, 2019
    Inventors: Sofien Bouaziz, Brian Amberg, Thibaut Weise, Patrick Snape, Stefan Brugger, Alex Mansfield, Reinhard Knothe, Thomas Kiser
  • Method of producing a reflective or refractive surface
    Patent number: 9576553
    Abstract: A method and apparatus for producing a reflective or refractive surface that reflects or refracts light shined thereon and reproduces on a screen a desired greyscale intensity image on which the reflective or refractive surface is based and a corresponding apparatus, wherein the method permits a reproduction of a reference grayscale image with adjustable precision.
    Type: Grant
    Filed: August 23, 2013
    Date of Patent: February 21, 2017
    Assignee: ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE
    Inventors: Mark Pauly, Thomas Kiser
  • METHOD OF PRODUCING A REFLECTIVE OR REFRACTIVE SURFACE
    Publication number: 20140071155
    Abstract: A method and apparatus for producing a reflective or refractive surface that reflects or refracts light shined thereon and reproduces on a screen a desired greyscale intensity image on which the reflective or refractive surface is based and a corresponding apparatus, wherein the method permits a reproduction of a reference grayscale image with adjustable precision.
    Type: Application
    Filed: August 23, 2013
    Publication date: March 13, 2014
    Inventors: MARK PAULY, THOMAS KISER