Patents by Inventor Deepak Vembar

Deepak Vembar 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: 11557085
    Abstract: Embodiments are directed to neural network processing for multi-object three-dimensional (3D) modeling. An embodiment of a computer-readable storage medium includes executable computer program instructions for obtaining data from multiple cameras, the data including multiple images, and generating a 3D model for 3D imaging based at least in part on the data from the cameras, wherein generating the 3D model includes one or more of performing processing with a first neural network to determine temporal direction based at least in part on motion of one or more objects identified in an image of the multiple images or performing processing with a second neural network to determine semantic content information for an image of the multiple images.
    Type: Grant
    Filed: December 4, 2020
    Date of Patent: January 17, 2023
    Assignee: Intel Corporation
    Inventors: Jill Boyce, Soethiha Soe, Selvakumar Panneer, Adam Lake, Nilesh Jain, Deepak Vembar, Glen J. Anderson, Varghese George, Carl Marshall, Scott Janus, Saurabh Tangri, Karthik Veeramani, Prasoonkumar Surti
  • Publication number: 20220392116
    Abstract: A mechanism is described for image frame rendering. An apparatus of embodiments, as described herein, includes one or more processors to receive a plurality of past image frames including a plurality of pixels, receive a predicted optical flow, generate a predicted frame and a confidence map associated with the predicted frame based on the plurality of past image frames and the predicted optical flow, render a first set of the plurality of pixels in the predicted frame based on the confidence map and adding the rendered pixels to the predicted frame to generate a final frame.
    Type: Application
    Filed: June 3, 2021
    Publication date: December 8, 2022
    Applicant: Intel Corporation
    Inventors: Deepak Vembar, Carl S. Marshall
  • Publication number: 20220092741
    Abstract: An apparatus and method for efficiently improving virtual/real interactions in augmented reality. For example, one embodiment of a method comprises: capturing a raw image including depth data; identifying one or more regions of interest based on a detected spatial proximity of one or more virtual objects and one or more real objects; generating a super-resolution map of the one or more regions of interest using machine-learning techniques or results thereof; detecting interactions between the virtual objects and the real objects using the super-resolution map; and performing one or more graphics processing or general purpose processing operations based on the detected interactions.
    Type: Application
    Filed: September 28, 2021
    Publication date: March 24, 2022
    Inventors: Zhengmin LI, Atsuo KUWAHARA, Deepak VEMBAR
  • Publication number: 20220058853
    Abstract: One embodiment provides for a graphics processor comprising a block of graphics compute units, a graphics processor pipeline coupled to the block of graphics compute units, and a programmable neural network unit including one or more neural network hardware blocks. The programmable neural network unit is coupled with the block of graphics compute units and the graphics processor pipeline. The one or more neural network hardware blocks include hardware to perform neural network operations and activation operations for a layer of a neural network. The programmable neural network unit can configure settings of one or more hardware blocks within the graphics processor pipeline based on a machine learning model trained to optimize performance of a set of workloads.
    Type: Application
    Filed: October 13, 2021
    Publication date: February 24, 2022
    Applicant: Intel Corporation
    Inventors: HUGUES LABBE, DARREL PALKE, SHERINE ABDELHAK, JILL BOYCE, VARGHESE GEORGE, SCOTT JANUS, ADAM LAKE, ZHIJUN LEI, ZHENGMIN LI, MIKE MACPHERSON, CARL MARSHALL, SELVAKUMAR PANNEER, PRASOONKUMAR SURTI, KARTHIK VEERAMANI, DEEPAK VEMBAR, VALLABHAJOSYULA SRINIVASA SOMAYAZULU
  • Patent number: 11151769
    Abstract: One embodiment provides for a graphics processor comprising a block of graphics compute units, a graphics processor pipeline coupled to the block of graphics compute units, and a programmable neural network unit including one or more neural network hardware blocks. The programmable neural network unit is coupled with the block of graphics compute units and the graphics processor pipeline. The one or more neural network hardware blocks include hardware to perform neural network operations and activation operations for a layer of a neural network. The programmable neural network unit can configure settings of one or more hardware blocks within the graphics processor pipeline based on a machine learning model trained to optimize performance of a set of workloads.
    Type: Grant
    Filed: August 9, 2019
    Date of Patent: October 19, 2021
    Assignee: Intel Corporation
    Inventors: Hugues Labbe, Darrel Palke, Sherine Abdelhak, Jill Boyce, Varghese George, Scott Janus, Adam Lake, Zhijun Lei, Zhengmin Li, Mike Macpherson, Carl Marshall, Selvakumar Panneer, Prasoonkumar Surti, Karthik Veeramani, Deepak Vembar, Vallabhajosyula Srinivasa Somayazulu
  • Patent number: 11138692
    Abstract: An apparatus and method for efficiently improving virtual/real interactions in augmented reality. For example, one embodiment of a method comprises: capturing a raw image including depth data; identifying one or more regions of interest based on a detected spatial proximity of one or more virtual objects and one or more real objects; generating a super-resolution map of the one or more regions of interest using machine-learning techniques or results thereof; detecting interactions between the virtual objects and the real objects using the super-resolution map; and performing one or more graphics processing or general purpose processing operations based on the detected interactions.
    Type: Grant
    Filed: November 15, 2019
    Date of Patent: October 5, 2021
    Assignee: INTEL CORPORATION
    Inventors: Zhengmin Li, Atsuo Kuwahara, Deepak Vembar
  • Publication number: 20210090327
    Abstract: Embodiments are directed to neural network processing for multi-object three-dimensional (3D) modeling. An embodiment of a computer-readable storage medium includes executable computer program instructions for obtaining data from multiple cameras, the data including multiple images, and generating a 3D model for 3D imaging based at least in part on the data from the cameras, wherein generating the 3D model includes one or more of performing processing with a first neural network to determine temporal direction based at least in part on motion of one or more objects identified in an image of the multiple images or performing processing with a second neural network to determine semantic content information for an image of the multiple images.
    Type: Application
    Filed: December 4, 2020
    Publication date: March 25, 2021
    Applicant: Intel Corporation
    Inventors: Jill Boyce, Soethiha Soe, Selvakamur Panneer, Adam Lake, Nilesh Jain, Deepak Vembar, Glen J. Anderson, Varghese George, Carl Marshall, Scott Janus, Saurabh Tangri, Karthik Veeramani, Prasoonkumar Surti
  • Patent number: 10861225
    Abstract: Embodiments are directed to neural network processing for multi-object three-dimensional (3D) modeling. An embodiment of a computer-readable storage medium includes executable computer program instructions for obtaining data from multiple cameras, the data including multiple images, and generating a 3D model for 3D imaging based at least in part on the data from the cameras, wherein generating the 3D model includes one or more of performing processing with a first neural network to determine temporal direction based at least in part on motion of one or more objects identified in an image of the multiple images or performing processing with a second neural network to determine semantic content information for an image of the multiple images.
    Type: Grant
    Filed: December 27, 2018
    Date of Patent: December 8, 2020
    Assignee: INTEL CORPORATION
    Inventors: Jill Boyce, Soethiha Soe, Selvakumar Panneer, Adam Lake, Nilesh Jain, Deepak Vembar, Glen J. Anderson, Varghese George, Carl Marshall, Scott Janus, Saurabh Tangri, Karthik Veeramani, Prasoonkumar Surti
  • Patent number: 10712834
    Abstract: Embodiments for providing a wearable device are generally described herein. A wearable device may include a processor having memory and communicatively coupled to a plurality of display areas; and an orientation sensing module communicatively coupled to the processor to determine at least one of an orientation and a location of at least one of the plurality of display areas with respect to a point of view of a user; wherein the processor provides a function for at least one of the plurality of display areas based on the determined at least one of the orientation and the location of at least one of the plurality of display areas by the orientation sensing module.
    Type: Grant
    Filed: August 28, 2017
    Date of Patent: July 14, 2020
    Assignee: INTEL CORPORATION
    Inventors: Giuseppe Raffa, Deepak Vembar, Glen J. Anderson, Ryan Scott Brotman, Jamie Sherman, Francisco Javier Fernandez
  • Publication number: 20200184602
    Abstract: An apparatus and method for efficiently improving virtual/real interactions in augmented reality. For example, one embodiment of a method comprises: capturing a raw image including depth data; identifying one or more regions of interest based on a detected spatial proximity of one or more virtual objects and one or more real objects; generating a super-resolution map of the one or more regions of interest using machine-learning techniques or results thereof; detecting interactions between the virtual objects and the real objects using the super-resolution map; and performing one or more graphics processing or general purpose processing operations based on the detected interactions.
    Type: Application
    Filed: November 15, 2019
    Publication date: June 11, 2020
    Inventors: Zhengmin LI, Atsuo KUWAHARA, Deepak VEMBAR
  • Publication number: 20200051309
    Abstract: One embodiment provides for a graphics processor comprising a block of graphics compute units, a graphics processor pipeline coupled to the block of graphics compute units, and a programmable neural network unit including one or more neural network hardware blocks. The programmable neural network unit is coupled with the block of graphics compute units and the graphics processor pipeline. The one or more neural network hardware blocks include hardware to perform neural network operations and activation operations for a layer of a neural network. The programmable neural network unit can configure settings of one or more hardware blocks within the graphics processor pipeline based on a machine learning model trained to optimize performance of a set of workloads.
    Type: Application
    Filed: August 9, 2019
    Publication date: February 13, 2020
    Applicant: Intel Corporation
    Inventors: HUGUES LABBE, DARREL PALKE, SHERINE ABDELHAK, JILL BOYCE, VARGHESE GEORGE, SCOTT JANUS, ADAM LAKE, ZHIJUN LEI, ZHENGMIN LI, MIKE MACPHERSON, CARL MARSHALL, SELVAKUMAR PANNEER, PRASOONKUMAR SURTI, KARTHIK VEERAMANI, DEEPAK VEMBAR, VALLABHAJOSYULA SRINIVASA SOMAYAZULU
  • Publication number: 20190362461
    Abstract: Embodiments described herein provide a method comprises constructing an application tool profile from a history of tools used by an application to create one or more documents, storing the application tool profile in a memory; and creating a customized application toolset for the application using the application tool profile. Other embodiments may be described and claimed.
    Type: Application
    Filed: August 9, 2019
    Publication date: November 28, 2019
    Applicant: Intel Corporation
    Inventors: VARGHESE GEORGE, JILL BOYCE, SELVAKUMAR PANNEER, DEEPAK VEMBAR, KARTHIK VEERAMANI, PRASOONKUMAR SURTI, SCOTT JANUS, SOETHIHA SOE, NILESH JAIN, SAURABH TANGRI, GLEN J. ANDERSON, ADAM LAKE, CARL MARSHALL
  • Patent number: 10482575
    Abstract: An apparatus and method for efficiently improving virtual/real interactions in augmented reality. For example, one embodiment of a method comprises: capturing a raw image including depth data; identifying one or more regions of interest based on a detected spatial proximity of one or more virtual objects and one or more real objects; generating a super-resolution map of the one or more regions of interest using machine-learning techniques or results thereof; detecting interactions between the virtual objects and the real objects using the super-resolution map; and performing one or more graphics processing or general purpose processing operations based on the detected interactions.
    Type: Grant
    Filed: September 28, 2017
    Date of Patent: November 19, 2019
    Assignee: INTEL CORPORATION
    Inventors: Zhengmin Li, Atsuo Kuwahara, Deepak Vembar
  • Publication number: 20190130639
    Abstract: Embodiments are directed to neural network processing for multi-object three-dimensional (3D) modeling. An embodiment of a computer-readable storage medium includes executable computer program instructions for obtaining data from multiple cameras, the data including multiple images, and generating a 3D model for 3D imaging based at least in part on the data from the cameras, wherein generating the 3D model includes one or more of performing processing with a first neural network to determine temporal direction based at least in part on motion of one or more objects identified in an image of the multiple images or performing processing with a second neural network to determine semantic content information for an image of the multiple images.
    Type: Application
    Filed: December 27, 2018
    Publication date: May 2, 2019
    Applicant: Intel Corporation
    Inventors: Jill Boyce, Soethiha Soe, Selva Panneer, Adam Lake, Nilesh Jain, Deepak Vembar, Glen J. Anderson, Varghese George, Carl Marshall, Scott Janus, Saurabh Tangri, Karthik Veeramani, Prasoonkumar Surti
  • Publication number: 20190096035
    Abstract: An apparatus and method for efficiently improving virtual/real interactions in augmented reality. For example, one embodiment of a method comprises: capturing a raw image including depth data; identifying one or more regions of interest based on a detected spatial proximity of one or more virtual objects and one or more real objects; generating a super-resolution map of the one or more regions of interest using machine-learning techniques or results thereof; detecting interactions between the virtual objects and the real objects using the super-resolution map; and performing one or more graphics processing or general purpose processing operations based on the detected interactions.
    Type: Application
    Filed: September 28, 2017
    Publication date: March 28, 2019
    Inventors: ZHENGMIN LI, ATSUO KUWAHARA, DEEPAK VEMBAR
  • Patent number: 9954857
    Abstract: A system and method for controlling access to a digital asset. A first host device is provided to a first host device owner and rights are determined to a digital asset. A digital charm is selected, wherein selecting includes granting to the digital charm certain rights to the digital asset. The digital charm is attached to the first host device to form a charm system, wherein attaching includes conferring, to the first host device owner, the rights to the digital asset that were granted to the digital charm.
    Type: Grant
    Filed: December 19, 2013
    Date of Patent: April 24, 2018
    Assignee: Intel Corporation
    Inventors: Rachel Hinman, Aleksander Magi, Glen J. Anderson, Ana Rosario, Ryan Scott Brotman, Cory J. Booth, Giuseppe Raffa, Jamie Sherman, Philip A. Muse, Jonathan J. Huang, Deepak Vembar
  • Publication number: 20180107289
    Abstract: Embodiments for providing a wearable device are generally described herein. A wearable device may include a processor having memory and communicatively coupled to a plurality of display areas; and an orientation sensing module communicatively coupled to the processor to determine at least one of an orientation and a location of at least one of the plurality of display areas with respect to a point of view of a user; wherein the processor provides a function for at least one of the plurality of display areas based on the determined at least one of the orientation and the location of at least one of the plurality of display areas by the orientation sensing module.
    Type: Application
    Filed: August 28, 2017
    Publication date: April 19, 2018
    Inventors: Giuseppe Raffa, Deepak Vembar, Glen J. Anderson, Ryan Scott Brotman, Jamie Sherman, Francisco Javier Fernandez
  • Patent number: 9886084
    Abstract: System and techniques for user input via elastic deformation of a material are described herein. The morphology of an elastic material may be observed with a sensor. The observations may include a first and a second morphological sample of the elastic material. The first and second morphological samples may be compared against each other to ascertain a variance. The variance may be filtered to produce an output. The output may be translated into a user input parameter. A device action corresponding to the user input parameter may be invoked.
    Type: Grant
    Filed: November 11, 2014
    Date of Patent: February 6, 2018
    Assignee: Intel Corporation
    Inventors: Deepak Vembar, Glen J. Anderson, Lenitra M. Durham, Kathy Yuen, Ryan Scott Brotman, Giuseppe Raffa
  • Patent number: 9746941
    Abstract: Embodiments for providing a wearable device are generally described herein. A wearable device may include a processor having memory and communicatively coupled to a plurality of display areas; and an orientation sensing module communicatively coupled to the processor to determine at least one of an orientation and a location of at least one of the plurality of display areas with respect to a point of view of a user; wherein the processor provides a function for at least one of the plurality of display areas based on the determined at least one of the orientation and the location of at least one of the plurality of display areas by the orientation sensing module.
    Type: Grant
    Filed: December 26, 2013
    Date of Patent: August 29, 2017
    Assignee: Intel Corporation
    Inventors: Giuseppe Raffa, Deepak Vembar, Glen J. Anderson, Ryan Scott Brotman, Jamie Sherman, Francisco Javier Fernandez
  • Publication number: 20160323271
    Abstract: A system and method for controlling access to a digital asset. A first host device is provided to a first host device owner and rights are determined to a digital asset. A digital charm is selected, wherein selecting includes granting to the digital charm certain rights to the digital asset. The digital charm is attached to the first host device to form a charm system, wherein attaching includes conferring, to the first host device owner, the rights to the digital asset that were granted to the digital charm.
    Type: Application
    Filed: December 19, 2013
    Publication date: November 3, 2016
    Inventors: Rachel Hinman, Aleksander Magi, Glen J. Anderson, Ana Rosario, Ryan Scott Brotman, Cory J. Booth, Giuseppe Beppe Raffa, Jamie Sherman, Philip A. Muse, Jonathan Jon Huang, Deepak Vembar