Patents by Inventor Mohamed ELGHARIB

Mohamed ELGHARIB 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).

  • Patent number: 10991150
    Abstract: A method of rendering a stereoscopic 3D image from a single image, including receiving a collection of pairs of 3D images including an input image and an output image that is a 3D pair of the input image, training a neural network composed of convolutional layers without any fully connected layers, with pairs of 3D images from the collection, to receive an input image and generate an output image that is a 3D pair of the input image, wherein the neural network is provided as an application on a computing device, receiving an input image and generating an output image that is a 3D pair of the input image by the neural network.
    Type: Grant
    Filed: November 6, 2018
    Date of Patent: April 27, 2021
    Assignees: MASSACHUSETTS INSTITUTE OF TECHNOLOGY, QATAR FOUNDATION FOR EDUCATION, SCIENCE AND COMMUNITY DEVELOPMENT
    Inventors: Mohamed Elgharib, Wojciech Matusik, Sung-Ho Bae, Mohamed Hefeeda
  • Patent number: 10834379
    Abstract: A wide spread adoption of 3D videos and technologies is hindered by the lack of high-quality 3D content. One promising solution to address this problem is to use automated 2D-to-3D conversion. However, current conversion methods, while general, produce low-quality results with artefacts that are not acceptable to many viewers. Creating a database of 3D stereoscopic videos with accurate depth is, however, very difficult. Computer generated content can be used to generate high-quality 3D video reference database for 2D-to-3D conversion. The method transfers depth information from frames in the 3D reference database to the target frame while respecting object boundaries. It computes depth maps from the depth gradients, and outputs a stereoscopic video.
    Type: Grant
    Filed: September 23, 2019
    Date of Patent: November 10, 2020
    Inventors: Mohamed M. Hefeeda, Kiana Ali Asghar Calagari, Mohamed Abdelaziz A Mohamed Elgharib, Wojciech Matusik, Piotr Didyk, Alexandre Kaspar
  • Publication number: 20200053345
    Abstract: A wide spread adoption of 3D videos and technologies is hindered by the lack of high-quality 3D content. One promising solution to address this problem is to use automated 2D-to-3D conversion. However, current conversion methods, while general, produce low-quality results with artefacts that are not acceptable to many viewers. Creating a database of 3D stereoscopic videos with accurate depth is, however, very difficult. Computer generated content can be used to generate high-quality 3D video reference database for 2D-to-3D conversion. The method transfers depth information from frames in the 3D reference database to the target frame while respecting object boundaries. It computes depth maps from the depth gradients, and outputs a stereoscopic video.
    Type: Application
    Filed: September 23, 2019
    Publication date: February 13, 2020
    Inventors: Mohamed M. HEFEEDA, Kiana Ali Asghar CALAGARI, Mohamed Abdelaziz A Mohamed ELGHARIB, Wojciech MATUSIK, Piotr DIDYK, Alexandre KASPAR
  • Publication number: 20190347847
    Abstract: A method of rendering a stereoscopic 3D image from a single image, including receiving a collection of pairs of 3D images including an input image and an output image that is a 3D pair of the input image, training a neural network composed of convolutional layers without any fully connected layers, with pairs of 3D images from the collection, to receive an input image and generate an output image that is a 3D pair of the input image, wherein the neural network is provided as an application on a computing device, receiving an input image and generating an output image that is a 3D pair of the input image by the neural network.
    Type: Application
    Filed: November 6, 2018
    Publication date: November 14, 2019
    Inventors: Mohamed ELGHARIB, Wojciech MATUSIK, Sung-Ho BAE, Mohamed HEFEEDA
  • Patent number: 10425634
    Abstract: A wide spread adoption of 3D videos and technologies is hindered by the lack of high-quality 3D content. One promising solution to address this problem is to use automated 2D-to-3D conversion. However, current conversion methods, while general, produce low-quality results with artefacts that are not acceptable to many viewers. Creating a database of 3D stereoscopic videos with accurate depth is, however, very difficult. Computer generated content can be used to generate high-quality 3D video reference database for 2D-to-3D conversion. The method transfers depth information from frames in the 3D reference database to the target frame while respecting object boundaries. It computes depth maps from the depth gradients, and outputs a stereoscopic video.
    Type: Grant
    Filed: August 3, 2016
    Date of Patent: September 24, 2019
    Inventors: Mohamed M. Hefeeda, Kiana Ali Asghar Calagari, Mohamed Abdelaziz A Mohamed Elgharib, Wojciech Matusik, Piotr Didyk, Alexandre Kaspar
  • Patent number: 10217187
    Abstract: The method for dynamic video magnification magnifies small motions occurring simultaneously within large motions. The method involves selecting a region of interest from a video for magnification. The region of interest is warped to obtain a stabilized sequence of frames that discounts large motions. Each frame of the stabilized sequence is decomposed to a foreground layer, a background layer, and an alpha matte layer, and each of the foreground and alpha matte layers is magnified. Then a magnified sequence is generated from the magnified layers using matte inversion. Any image holes in the magnified sequence are filled in using texture synthesis. Finally, the magnified sequence is de-warped to the original space-time coordinates.
    Type: Grant
    Filed: June 3, 2016
    Date of Patent: February 26, 2019
    Assignees: QATAR FOUNDATION FOR EDUCATION, SCIENCE AND IMMUNITY DEVELOPMENT, MASSACHUSETTS INSTITUTE OF TECHNOLOGY
    Inventors: Mohamed Abdelaziz A. Mohamed Elgharib, Mohamed M. Hefeeda, William T. Freeman, Frederic Durand
  • Publication number: 20180227574
    Abstract: A wide spread adoption of 3D videos and technologies is hindered by the lack of high-quality 3D content. One promising solution to address this problem is to use automated 2D-to-3D conversion. However, current conversion methods, while general, produce low-quality results with artefacts that are not acceptable to many viewers. Creating a database of 3D stereoscopic videos with accurate depth is, however, very difficult. Computer generated content can be used to generate high-quality 3D video reference database for 2D-to-3D conversion. The method transfers depth information from frames in the 3D reference database to the target frame while respecting object boundaries. It computes depth maps from the depth gradients, and outputs a stereoscopic video.
    Type: Application
    Filed: August 3, 2016
    Publication date: August 9, 2018
    Inventors: Mohamed M. HEFEEDA, Kiana Ali Asghar CALAGARI, Mohamed Abdelaziz a mohamed ELGHARIB, Wojciech MATUSIK, Piotr DIDKY, Alexandre KASPAR
  • Publication number: 20180225803
    Abstract: The method for dynamic video magnification magnifies small motions occurring simultaneously within large motions. The method involves selecting a region of interest from a video for magnification. The region of interest is warped to obtain a stabilized sequence of frames that discounts large motions. Each frame of the stabilized sequence is decomposed to a foreground layer, a background layer, and an alpha matte layer, and each of the foreground and alpha matte layers is magnified. Then a magnified sequence is generated from the magnified layers using matte inversion. Any image holes in the magnified sequence are filled in using texture synthesis. Finally, the magnified sequence is de-warped to the original space-time coordinates.
    Type: Application
    Filed: June 3, 2016
    Publication date: August 9, 2018
    Applicants: QATAR FOUNDATION FOR EDUCATION, SCIENCE AND COMMUNITY DEVELOPMENT, MASSACHUSETTS INSTITUTE OF TECHNOLOGY
    Inventors: MOHAMED ABDELAZIZ A. MOHAMED ELGHARIB, MOHAMED M. HEFEEDA, WILLIAM T. FREEMAN, FREDERIC DURAND