Patents by Inventor Atul Puri

Atul Puri 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).

  • Publication number: 20180278933
    Abstract: A system and method for quality restoration filtering is described that can be used either in conjunction with video coding, or standalone for postprocessing. It uses wiener filtering approach in conjunction with an efficient codebook representation.
    Type: Application
    Filed: March 13, 2018
    Publication date: September 27, 2018
    Applicant: Intel Corporation
    Inventors: Atul Puri, Daniel Socek
  • Publication number: 20180205968
    Abstract: Techniques related to quality restoration filtering for video coding are described.
    Type: Application
    Filed: October 24, 2017
    Publication date: July 19, 2018
    Inventors: Atul Puri, Daniel Socek
  • Patent number: 10027962
    Abstract: A quantizer and dequantizer for use in a video coding system that applies non linear, piece-wise linear scaling functions to video information signals based on a value of a variable quantization parameter. The quantizer and dequantizer apply different non linear, piece-wise linear scaling functions to a DC luminance signal, a DC chrominance signal and an AC chrominance signal. A code for reporting updates of the value of the quantization parameter is interpreted to require larger changes when the quantization parameter initially is large and smaller changes when the quantization parameter initially is small.
    Type: Grant
    Filed: July 11, 2016
    Date of Patent: July 17, 2018
    Assignee: AT&T INTELLECTUAL PROPERTY II, L.P.
    Inventors: Barin Geoffry Haskell, Atul Puri, Robert Lewis Schmidt
  • Patent number: 10021392
    Abstract: Techniques related to content adaptive bi-directional or functionally predictive multi-pass pictures for high efficiency next generation video coding.
    Type: Grant
    Filed: December 28, 2013
    Date of Patent: July 10, 2018
    Assignee: Intel Corporation
    Inventor: Atul Puri
  • Patent number: 10009610
    Abstract: Techniques related to content adaptive prediction and entropy coding of motion vectors are described.
    Type: Grant
    Filed: July 18, 2017
    Date of Patent: June 26, 2018
    Assignee: Intel Corporation
    Inventors: Atul Puri, Daniel Socek, Chang Kee Choi
  • Publication number: 20180176577
    Abstract: Techniques related to content adaptive gain compensated prediction for next generation video coding are described.
    Type: Application
    Filed: February 24, 2014
    Publication date: June 21, 2018
    Inventor: ATUL PURI
  • Patent number: 9973758
    Abstract: Techniques related to content adaptive entropy coding are described. A technique for video coding may include obtaining first and second video data for entropy encoding such that the first and second video data comprise different data types, determining a first entropy encoding technique for the first video data such that the first entropy encoding technique comprises at least one of an adaptive symbol-run video length coding technique or an adaptive proxy variable length coding technique, entropy encoding the first video data using the first encoding technique to generate first compressed video data and the second video data using a second encoding technique to generate second compressed video data, and assembling the first compressed video data and the second compressed video data to generate an output bitstream.
    Type: Grant
    Filed: December 24, 2013
    Date of Patent: May 15, 2018
    Assignee: Intel Corporation
    Inventor: Atul Puri
  • Patent number: 9973757
    Abstract: Techniques related to content adaptive predictive and functionally predictive pictures with modified references for next generation video coding are described.
    Type: Grant
    Filed: December 27, 2013
    Date of Patent: May 15, 2018
    Assignee: Intel Corporation
    Inventors: Atul Puri, Neelesh N. Gokhale
  • Patent number: 9955176
    Abstract: Techniques related to intra video frame or image coding using wavelets and (Advanced Video Coding) AVC, modified AVC, VPx, modified VPx, or modified High Efficiency Video Coding (HEVC) are discussed. Such techniques may include wavelet decomposition of a frame or image to generate subbands and coding the subbands using compliant and/or modified coding techniques.
    Type: Grant
    Filed: November 30, 2015
    Date of Patent: April 24, 2018
    Assignee: Intel Corporation
    Inventor: Atul Puri
  • Patent number: 9942572
    Abstract: Techniques related to fusion improvement filtering of prediction signals for video coding are described.
    Type: Grant
    Filed: July 17, 2014
    Date of Patent: April 10, 2018
    Assignee: Intel Corporation
    Inventors: Atul Puri, Daniel Socek
  • Patent number: 9924201
    Abstract: A system and method of removing noise in a bitstream is disclosed. Based on the segment classifications of a bitstream, each segment or portion is encoded with a different encoder associated with the portion model and chosen from a plurality of encoders. The coded bitstream for each segment includes information regarding which encoder was used to encode that segment. A circuit for removing noise in video content includes a first filter connected to a first input switch and a first output switch, the first filter being in parallel with a first pass-through line, a second filter connected to a second input switch and a second output switch, the second filter connected in parallel with a second pass-through line, and a third filter connected to a third input switch in a third output switch.
    Type: Grant
    Filed: March 20, 2017
    Date of Patent: March 20, 2018
    Assignee: AT&T Intellectual Property II, L.P.
    Inventors: Atul Puri, Mehmet Reha Civanlar
  • Patent number: 9912958
    Abstract: Techniques related to adaptive precision and filtering motion compensation for video coding may include, for example, determining, via a motion compensated filtering predictor module, a motion compensation prediction precision associated with at least a portion of a current picture being decoded, where the motion compensation prediction precision comprises at least one of a quarter pel precision or an eighth pel precision. Predicted pixel data of a predicted partition associated with a prediction partition of the current picture may be generated, via the motion compensated filtering predictor module, by filtering a portion of a decoded reference picture based at least in part on the motion compensation prediction precision. Prediction partitioning indicators associated with the prediction partition and a motion vector indicating a positional difference between the prediction partition and an associated partition of the decoded reference picture may be coded, via an entropy encoder, into a bitstream.
    Type: Grant
    Filed: July 17, 2014
    Date of Patent: March 6, 2018
    Assignee: Intel Corporation
    Inventors: Atul Puri, Neelesh N. Gokhale
  • Patent number: 9912947
    Abstract: A system and method for quality restoration filtering is described that can be used either in conjunction with video coding, or standalone for postprocessing. It uses wiener filtering approach in conjunction with an efficient codebook representation.
    Type: Grant
    Filed: March 13, 2015
    Date of Patent: March 6, 2018
    Assignee: Intel Corporation
    Inventors: Atul Puri, Daniel Socek
  • Patent number: 9894372
    Abstract: Techniques related to super resolution prediction generation for video coding are described.
    Type: Grant
    Filed: July 17, 2014
    Date of Patent: February 13, 2018
    Assignee: Intel Corporation
    Inventors: Atul Puri, Neelesh N. Gokhale
  • Patent number: 9883198
    Abstract: Techniques related to video codec architecture for next generation video are described.
    Type: Grant
    Filed: November 13, 2013
    Date of Patent: January 30, 2018
    Assignee: Intel Corporation
    Inventors: Atul Puri, Neelesh Gokhale
  • Patent number: 9870801
    Abstract: An interactive video/multimedia application (IVM application) may specify one or more media assets for playback. The IVM application may define the rendering, composition, and interactivity of one or more the assets, such as video. Video multimedia application data (IVMA data may) be used to define the behavior of the IVM application. The IVMA data may be embodied as a standalone file in a text or binary, compressed format. Alternatively, the IVMA data may be embedded within other media content. A video asset used in the IVM application may include embedded, content-aware metadata that is tightly coupled to the asset. The IVM application may reference the content-aware metadata embedded within the asset to define the rendering and composition of application display elements and user-interactivity features. The interactive video/multimedia application (defined by the video and multimedia application data) may be presented to a viewer in a player application.
    Type: Grant
    Filed: December 8, 2015
    Date of Patent: January 16, 2018
    Assignee: INTEL CORPORATION
    Inventors: Atul Puri, Hari Kalva
  • Patent number: 9866845
    Abstract: A method of content adaptive encoding video comprising segmenting video content into segments based on predefined classifications or models. Based on the segment classifications, each segment is encoded with a different encoder chosen from a plurality of encoders. Each encoder is associated with a model. The chosen encoder is particularly suited to encoding the unique subject matter of the segment. The coded bit-stream for each segment includes information regarding which encoder was used to encode that segment. A matching decoder of a plurality of decoders is chosen using the information in the coded bitstream to decode each segment using a decoder suited for the classification or model of the segment. If scenes exist which do not fall in a predefined classification, or where classification is more difficult based on the scene content, these scenes are segmented, coded and decoded using a generic coder and decoder.
    Type: Grant
    Filed: September 23, 2016
    Date of Patent: January 9, 2018
    Assignee: AT&T Intellectual Property II, L.P.
    Inventors: Atul Puri, Mehmet Reha Civanlar
  • Patent number: 9838707
    Abstract: A method and apparatus for variable accuracy inter-picture timing specification for digital video encoding is disclosed. Specifically, the present invention discloses a system that allows the relative timing of nearby video pictures to be encoded in a very efficient manner. In one embodiment, the display time difference between a current video picture and a nearby video picture is determined. The display time difference is then encoded into a digital representation of the video picture. In a preferred embodiment, the nearby video picture is the most recently transmitted stored picture. For coding efficiency, the display time difference may be encoded using a variable length coding system or arithmetic coding. In an alternate embodiment, the display time difference is encoded as a power of two to reduce the number of bits transmitted.
    Type: Grant
    Filed: November 1, 2016
    Date of Patent: December 5, 2017
    Assignee: APPLE INC.
    Inventors: Barin Geoffry Haskell, David William Singer, Adriana Dumitras, Atul Puri
  • Publication number: 20170339409
    Abstract: Techniques related to improved video coding based on skin tone detection are discussed. Such techniques may include selecting from static skin probability histograms and/or a dynamic skin probability histogram based on a received video frame, generating a skin tone region based on the selected skin probability histogram and a face region of the video frame, and encoding the video frame based on the skin tone region to generate a coded bitstream.
    Type: Application
    Filed: May 23, 2016
    Publication date: November 23, 2017
    Inventors: Daniel SOCEK, Atul PURI
  • Publication number: 20170339417
    Abstract: Techniques related to improved video coding based on face detection, region extraction, and tracking are discussed. Such techniques may include performing a facial search of a video frame to determine candidate face regions in the video frame, testing the candidate face regions based on skin tone information to determine valid and invalid face regions, rejecting invalid face regions, and encoding the video frame based on valid face regions to generate a coded bitstream.
    Type: Application
    Filed: May 23, 2016
    Publication date: November 23, 2017
    Inventors: Atul PURI, Daniel SOCEK