Patents by Inventor Anita Rau

Anita Rau 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).

  • DETERMINING VISUAL OVERLAP OF IMAGES BY USING BOX EMBEDDINGS
    Publication number: 20240046610
    Abstract: An image matching system for determining visual overlaps between images by using box embeddings is described herein. The system receives two images depicting a 3D surface with different camera poses. The system inputs the images (or a crop of each image) into a machine learning model that outputs a box encoding for the first image and a box encoding for the second image. A box encoding includes parameters defining a box in an embedding space. Then the system determines an asymmetric overlap factor that measures asymmetric surface overlaps between the first image and the second image based on the box encodings. The asymmetric overlap factor includes an enclosure factor indicating how much surface from the first image is visible in the second image and a concentration factor indicating how much surface from the second image is visible in the first image.
    Type: Application
    Filed: October 13, 2023
    Publication date: February 8, 2024
    Inventors: Anita Rau, Guillermo Garcia-Hernando, Gabriel J. Brostow, Daniyar Turmukhambetov
  • Determining visual overlap of images by using box embeddings
    Patent number: 11836965
    Abstract: An image matching system for determining visual overlaps between images by using box embeddings is described herein. The system receives two images depicting a 3D surface with different camera poses. The system inputs the images (or a crop of each image) into a machine learning model that outputs a box encoding for the first image and a box encoding for the second image. A box encoding includes parameters defining a box in an embedding space. Then the system determines an asymmetric overlap factor that measures asymmetric surface overlaps between the first image and the second image based on the box encodings. The asymmetric overlap factor includes an enclosure factor indicating how much surface from the first image is visible in the second image and a concentration factor indicating how much surface from the second image is visible in the first image.
    Type: Grant
    Filed: August 10, 2021
    Date of Patent: December 5, 2023
    Assignee: NIANTIC, INC.
    Inventors: Anita Rau, Guillermo Garcia-Hernando, Gabriel J. Brostow, Daniyar Turmukhambetov
  • DETERMINING VISUAL OVERLAP OF IMAGES BY USING BOX EMBEDDINGS
    Publication number: 20220051048
    Abstract: An image matching system for determining visual overlaps between images by using box embeddings is described herein. The system receives two images depicting a 3D surface with different camera poses. The system inputs the images (or a crop of each image) into a machine learning model that outputs a box encoding for the first image and a box encoding for the second image. A box encoding includes parameters defining a box in an embedding space. Then the system determines an asymmetric overlap factor that measures asymmetric surface overlaps between the first image and the second image based on the box encodings. The asymmetric overlap factor includes an enclosure factor indicating how much surface from the first image is visible in the second image and a concentration factor indicating how much surface from the second image is visible in the first image.
    Type: Application
    Filed: August 10, 2021
    Publication date: February 17, 2022
    Inventors: Anita Rau, Guillermo Garcia-Hernando, Gabriel J. Brostow, Daniyar Turmukhambetov