Patents by Inventor Jill Boyce

Jill Boyce 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).

  • Video analytics encoding for improved efficiency of video processing and compression
    Patent number: 10951903
    Abstract: Embodiments are generally directed to video analytics encoding for improved efficiency of video processing and compression. An embodiment of an apparatus includes a memory to store data, including data for video streaming, and a video processing mechanism, wherein the video processing mechanism is to analyze video data and generate video analytics, generate metadata representing the video analytics and insert the generated video analytics metadata into a message, and transmit the video data and the metadata to a succeeding apparatus or system in a video analytics pipeline, the video data being compressed video data.
    Type: Grant
    Filed: December 28, 2018
    Date of Patent: March 16, 2021
    Assignee: INTEL CORPORATION
    Inventors: Palanivel Guruva Reddiar, Jill Boyce
  • Removal of projection noise and point-based rendering
    Patent number: 10922832
    Abstract: Embodiments described herein provide an apparatus comprising a processor to divide a first image projection into a plurality of regions, the plurality of regions comprising a plurality of points, determine an accuracy rating for the plurality of regions, and apply one of a first rendering technique to a first region in the plurality of regions when the accuracy rating for the first region in the plurality of regions fails to meet an accuracy threshold or a second rendering technique to the first region in the plurality of regions when the accuracy rating for the first region in the plurality of regions meets an accuracy threshold, and a memory communicatively coupled to the processor. Other embodiments may be described and claimed.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: February 16, 2021
    Assignee: INTEL CORPORATION
    Inventors: Jason Tanner, Kai Xiao, Jill Boyce, Narayan Biswal, Jeffrey Tripp
  • Video refinement mechanism
    Patent number: 10911799
    Abstract: An apparatus to facilitate processing video bit stream data is disclosed. The apparatus includes one or more processors to decode point cloud data, reconstruct the decoded point cloud data and fill one or more holes in reconstructed point cloud frame data using patch metadata included in the decoded point cloud data and a memory communicatively coupled to the one or more processors.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: February 2, 2021
    Assignee: Intel Corporation
    Inventors: Jill Boyce, Scott Janus, Prasoonkumar Surti, Stanley Baran, Michael Apodaca, Srikanth Potluri, Hugues Labbe, Jong Dae Oh, Gokcen Cilingir, Archie Sharma, Jeffrey Tripp, Jason Ross, Barnan Das
  • Surface normal vector processing mechanism
    Patent number: 10893299
    Abstract: An apparatus to facilitate processing video bit stream data is disclosed. The apparatus includes one or more processors to encode surface normals data with point cloud geometry data included in the video bit stream data for reconstruction of objects within the video bit stream data based on the surface normals data and a memory communicatively coupled to the one or more processors.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: January 12, 2021
    Assignee: Intel Corporation
    Inventors: Jill Boyce, Scott Janus, Itay Kaufman, Archie Sharma, Stanley Baran, Michael Apodaca, Prasoonkumar Surti, Srikanth Potluri, Barnan Das, Hugues Labbe, Jong Dae Oh, Gokcen Cilingir, Maria Bortman, Tzach Ashkenazi, Jonathan Distler, Atul Divekar, Mayuresh M. Varerkar, Narayan Biswal, Nilesh V. Shah, Atsuo Kuwahara, Kai Xiao, Jason Tanner, Jeffrey Tripp
  • Selective packing of patches for immersive video
    Patent number: 10887574
    Abstract: Embodiments are generally directed to selective packing of patches for immersive video. An embodiment of a processing system includes one or more processor cores; and a memory to store data for immersive video, the data including a plurality of patches for multiple projection directions. The system is select the patches for packing, the selection of the patches based at least in part on which of the multiple projection directions is associated with each of the patches. The system is to encode the patches into one or more coded pictures according to the selection of the patches.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: January 5, 2021
    Assignee: INTEL CORPORATION
    Inventors: Eyal Ruhm, Jill Boyce, Asaf J. Shenberg
  • 3D renderer to video encoder pipeline for improved visual quality and low latency
    Patent number: 10881956
    Abstract: Techniques related to the render and encode of graphics frames representative of 3D video games are discussed. Such techniques include translating one or more of a transparency map, a depth map, a color compression map, or a motion field used to encode a graphics frame to encode parameters and encoding the first graphics frame using the encode parameters to generate a bitstream.
    Type: Grant
    Filed: December 28, 2018
    Date of Patent: January 5, 2021
    Assignee: Intel Corporation
    Inventors: Tomasz Madajczak, Jason Tanner, Jill Boyce, Changliang Wang, Maciej Oleksy, James Varga, Jr.
  • Video cluster encoding for multiple resolutions and bitrates with performance and quality enhancements
    Patent number: 10869041
    Abstract: Techniques related to video cluster encoding are discussed. Such techniques include encoding the video at a first resolution and first bitrate, translating block based coding parameters corresponding thereto to block based encode controls for encode of the same video at a second resolution or a second bitrate, and encoding the video at the second resolution and/or bitrate using the encode controls.
    Type: Grant
    Filed: March 29, 2019
    Date of Patent: December 15, 2020
    Assignee: Intel Corporation
    Inventors: Jason Tanner, Jill Boyce, David Steffy
  • Neural network processing for multi-object 3D modeling
    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
  • Patch processing mechanism
    Patent number: 10846814
    Abstract: An apparatus to facilitate processing video bit stream data is disclosed. The apparatus includes one or more processors to decode occupancy map data and auxiliary patch information and generate a plurality of patch video frames based on patch data decoded from the occupancy map data and auxiliary patch information, and a memory communicatively coupled to the one or more processors.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: November 24, 2020
    Assignee: Intel Corporation
    Inventors: Jill Boyce, Sang-hee Lee, Scott Janus, Stanley Baran, Michael Apodaca, Prasoonkumar Surti, Srikanth Potluri, Atsuo Kuwahara, Kai Xiao, Jason Tanner, Gokcen Cilingir, Archie Sharma, Jeffrey Tripp, Jason Ross, Barnan Das
  • Neural network based patch blending for immersive video
    Patent number: 10819968
    Abstract: Embodiments are generally directed to neural network based patch blending for immersive video. An embodiment of a system includes one or more processor cores; a memory to store data for images in immersive video; and a neural network training framework. The neural network training framework is to generate a trained neural network for blending of a view of an object with patches generated for one or more detected occlusions for the object.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: October 27, 2020
    Assignee: INTEL CORPORATION
    Inventors: Ben Raziel, Asaf Shiloni, Gilad Bauman, Jill Boyce, Tzach Ashkenazi, Ilan Beer, Eytan Kats
  • Generating 2D video from 360 video
    Patent number: 10791373
    Abstract: A semiconductor package apparatus may include technology to aggregate region of interest information for omni-directional video content from two or more sources, select video information from the omni-directional video content based on the aggregated region of interest information, and generate one or more two-dimensional videos based on the selected video information. Other embodiments are disclosed and claimed.
    Type: Grant
    Filed: December 29, 2017
    Date of Patent: September 29, 2020
    Assignee: Intel Corporation
    Inventors: Karthik Veeramani, Rajneesh Chowdhury, Jill Boyce, Rajesh Poornachandran
  • METHODS AND ARRANGEMENTS TO IDENTIFY ACTIVATION PROFILE CONTEXT IN TRAINING DATA
    Publication number: 20200302301
    Abstract: Logic may determine a specific performance of a neural network based on an event and may present the specific performance to provide a user with an explanation of the inference by a machine learning model such as a neural network. Logic may determine a first activation profile associated with the event, the first activation profile based on activation of nodes in one or more layers of the neural network during inference to generate an output. Logic may correlate the first activation profile against a second activation profile associated with a first training sample of training data. Logic may determine that the first training sample is associated with the event based on the correlation. Logic may output an indicator to identify the first training sample as being associated with the event.
    Type: Application
    Filed: June 5, 2020
    Publication date: September 24, 2020
    Applicant: Intel Corporation
    Inventors: Glen J. Anderson, Rajesh Poornachandran, Ignacio Alvarez, Giuseppe Raffa, Jill Boyce, Ankur Agrawal, Kshitij Doshi
  • DETERMINISTIC NEURAL NETWORKING INTEROPERABILITY
    Publication number: 20200175396
    Abstract: Embodiments described herein provide a general purpose graphics processing device, comprising a general purpose graphics processing compute block to process a workload including graphics or compute operations, a memory, and a neural network processing unit to define a profile for a reference inference engine, the profile identifying a group of operations which may be implemented by the reference inference engine, define one or more levels for the reference inference engine, the one or more levels identifying a bit depth of operation for the reference inference engine, and store the profile at the one or more levels for the reference inference engine in a computer readable memory. Other embodiments may be described and claimed.
    Type: Application
    Filed: December 4, 2018
    Publication date: June 4, 2020
    Applicant: Intel Corporation
    Inventor: Jill Boyce
  • MULTI-DIMENSIONAL VIDEO TRANSCODING
    Publication number: 20200154121
    Abstract: An example apparatus for transcoding multi-dimensional video includes a multi-dimensional video decoder to decode a first bitstream of multi-dimensional video. The apparatus also includes a transcoder to transcode the decoded first bitstream to generate transcoded multi-dimensional data. The apparatus also further includes a multi-dimensional video encoder to generate a second bitstream based on the transcoded multi-dimensional data.
    Type: Application
    Filed: January 10, 2020
    Publication date: May 14, 2020
    Inventors: Jill Boyce, Basel Salahieh
  • POINT CLOUD CODING STANDARD CONFORMANCE DEFINITION IN COMPUTING ENVIRONMENTS
    Publication number: 20200120347
    Abstract: A mechanism is described for facilitating defining of interoperability signaling and conformance points for the PCC standard in computing environments. A computing device of embodiments, as described herein, includes a decoder to decode a compressed bitstream of video data representing a point cloud, point cloud reconstructor circuitry to reconstruct a point cloud from the decoded patch video data, a syntax element parser to receive at least one syntax element representing interoperability signaling in the compressed bitstream to indicate the number of points in one or more pictures of the video data, and processing hardware to determine if the number of points in the one or more pictures of the compressed bitstream is within the conformance limits of the point cloud reconstructor circuitry.
    Type: Application
    Filed: October 8, 2019
    Publication date: April 16, 2020
    Applicant: Intel Corporation
    Inventor: Jill Boyce
  • GRAPHICS ARCHITECTURE INCLUDING A NEURAL NETWORK PIPELINE
    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
  • High layer syntax for temporal scalability
    Patent number: 10560706
    Abstract: Disclosed are techniques for temporal scalable video coding. By including a temporal_switching_point_flag and/or a temporal_nesting_flag into a normative part of the scalable bitstream, reference picture management in decoder can be simplified, and media-aware network elements and decoder can easily identify those pictures from which onward a higher temporal layer can be added.
    Type: Grant
    Filed: June 25, 2018
    Date of Patent: February 11, 2020
    Assignee: Vidyo, Inc.
    Inventors: Jill Boyce, Danny Hong
  • VIDEO PROCESSING MECHANISM
    Publication number: 20200043121
    Abstract: An apparatus to facilitate processing video bit stream data is disclosed. The apparatus includes one or more processors to decode occupancy map data and auxiliary patch information and generate a plurality of patch video frames based on patch data decoded from the occupancy map data and auxiliary patch information, and a memory communicatively coupled to the one or more processors.
    Type: Application
    Filed: July 31, 2018
    Publication date: February 6, 2020
    Applicant: Intel Corporation
    Inventors: Jill Boyce, Sang-hee Lee, Scott Janus, Stanley Baran, Michael Apodaca, Prasoonkumar Surti, Srikanth Potluri, Atsuo Kuwahara, Kai Xiao, Jason Tanner, Gokcen Cilingir, Archie Sharma, Jeffrey Tripp, Jason Ross, Barnan Das
  • REDUCED RENDERING OF SIX-DEGREE OF FREEDOM VIDEO
    Publication number: 20200045292
    Abstract: Embodiments described herein provide for techniques to reduce the complexity of rendering immersive 3D video content. One embodiment provides for an apparatus comprising one or more processors to receive a data set that represents a two-dimensional encoding of planar projections of a frame of a three-dimensional video, decode the two-dimensional encoding into texture data, geometry data, and metadata, determine, based on the metadata, a visibility status and an occupancy status for a sample position in the three-dimensional video, and render video data for the sample position when the sample position is visible and occupied.
    Type: Application
    Filed: July 31, 2018
    Publication date: February 6, 2020
    Applicant: Intel Corporation
    Inventor: Jill Boyce
  • NEURAL NETWORK BASED PATCH BLENDING FOR IMMERSIVE VIDEO
    Publication number: 20200045289
    Abstract: Embodiments are generally directed to neural network based patch blending for immersive video. An embodiment of a system includes one or more processor cores; a memory to store data for images in immersive video; and a neural network training framework. The neural network training framework is to generate a trained neural network for blending of a view of an object with patches generated for one or more detected occlusions for the object.
    Type: Application
    Filed: July 31, 2018
    Publication date: February 6, 2020
    Applicant: Intel Corporation
    Inventors: Ben Raziel, Asaf Shiloni, Gilad Bauman, Jill Boyce, Tzach Ashkenazi, Ilan Beer, Eytan Kats