Patents by Inventor Mohammed E. Fathy Salem

Mohammed E. Fathy Salem 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).

  • Dense three-dimensional correspondence estimation with multi-level metric learning and hierarchical matching
    Patent number: 10832084
    Abstract: A method for estimating dense 3D geometric correspondences between two input point clouds by employing a 3D convolutional neural network (CNN) architecture is presented. The method includes, during a training phase, transforming the two input point clouds into truncated distance function voxel grid representations, feeding the truncated distance function voxel grid representations into individual feature extraction layers with tied weights, extracting low-level features from a first feature extraction layer, extracting high-level features from a second feature extraction layer, normalizing the extracted low-level features and high-level features, and applying deep supervision of multiple contrastive losses and multiple hard negative mining modules at the first and second feature extraction layers.
    Type: Grant
    Filed: July 30, 2019
    Date of Patent: November 10, 2020
    Assignee: NEC Corporation
    Inventors: Quoc-Huy Tran, Mohammed E. Fathy Salem, Muhammad Zeeshan Zia, Paul Vernaza, Manmohan Chandraker
  • DENSE THREE-DIMENSIONAL CORRESPONDENCE ESTIMATION WITH MULTI-LEVEL METRIC LEARNING AND HIERARCHICAL MATCHING
    Publication number: 20200058156
    Abstract: A method for estimating dense 3D geometric correspondences between two input point clouds by employing a 3D convolutional neural network (CNN) architecture is presented. The method includes, during a training phase, transforming the two input point clouds into truncated distance function voxel grid representations, feeding the truncated distance function voxel grid representations into individual feature extraction layers with tied weights, extracting low-level features from a first feature extraction layer, extracting high-level features from a second feature extraction layer, normalizing the extracted low-level features and high-level features, and applying deep supervision of multiple contrastive losses and multiple hard negative mining modules at the first and second feature extraction layers.
    Type: Application
    Filed: July 30, 2019
    Publication date: February 20, 2020
    Inventors: Quoc-Huy Tran, Mohammed E. Fathy Salem, Muhammad Zeeshan Zia, Paul Vernaza, Manmohan Chandraker