Patents by Inventor Rohit Puri

Rohit 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).

  • Patent number: 7526025
    Abstract: A method and apparatus for encoding video frames is described. In one embodiment, an encoding method includes jointly transforming a set of pixels into high-pass data using an orthonormal transform. The set of pixels includes at least one reference pixel and predicted pixels. The method further includes generating low-pass data using the reference pixel and the high-pass data.
    Type: Grant
    Filed: October 22, 2004
    Date of Patent: April 28, 2009
    Assignees: Sony Corporation, Sony Electronics Inc.
    Inventors: Deepak S. Turaga, Rohit Puri, Ali J. Tabatabai
  • Publication number: 20080204287
    Abstract: Systems and methods for optimizing system performance in variable length decoding systems are described. Embodiments are described in which decode tables are analyzed and elements of the tables sorted by probability of occurrence. Storage of elements can be determined by probability of occurrence and embodiments of the present invention can optimize system efficiency by storing most likely entries into fast-memory and least likely entries in slowest memory. In certain embodiments, a single large table is provided that cannot fit into decoder fast-memory. In some embodiments, individual elements can be optimized for storage in fast-memory by selecting more frequently occurring entries or groups of entries into decoder memory.
    Type: Application
    Filed: January 29, 2008
    Publication date: August 28, 2008
    Applicant: NVIDIA CORPORATION
    Inventors: Rohit Puri, Partha Sriram
  • Patent number: 7400774
    Abstract: Encoding digital data by using cues at a decoder. An encoder selects an index to indicate a target codeword from the complete space of all codewords to a decoder. The index identifies a group or a set of codewords that contain the target codeword. The sets are represented by a bit-length that is smaller than the code word bit-length thus achieving compression. Two or more codewords in such a set are separated by a predetermined distance and all such sets of codewords considered together form the complete space of all codewords. The encoder sends syntax information, including the index, to specify the decoding. The decoder then uses a set of candidate cues in a comparison operation to determine the target codeword from the indexed set. Processing complexity can be allocated among the encoder, decoder and other possible devices as, for example, in a digital network.
    Type: Grant
    Filed: August 29, 2003
    Date of Patent: July 15, 2008
    Assignee: The Regents of the University of California
    Inventors: Rohit Puri, Kannan Ramchandran
  • Patent number: 7324026
    Abstract: Systems and methods for optimizing system performance in variable length decoding systems are described. Embodiments are described in which decode tables are analyzed and elements of the tables sorted by probability of occurrence. Storage of elements can be determined by probability of occurrence and embodiments of the present invention can optimize system efficiency by storing most likely entries into fast-memory and least likely entries in slowest memory. In certain embodiments, a single large table is provided that cannot fit into decoder fast-memory. In some embodiments, individual elements can be optimized for storage in fast-memory by selecting more frequently occurring entries or groups of entries into decoder memory.
    Type: Grant
    Filed: May 19, 2006
    Date of Patent: January 29, 2008
    Assignee: Nvidia Corporation
    Inventors: Rohit Puri, Partha Sriram
  • Publication number: 20070285285
    Abstract: A system for compressing digital data by representing a portion of it predictionally and transformationally as a block of transform coefficients, then quantizing that block selectively into a set of encoding symbols based on an indication whether the transform coefficients represent the portion as having a particular characteristic, and then by encoding the set of encoding symbols into a data bit stream. In particular, frequency may be used as the characteristic of the digital data in many applications.
    Type: Application
    Filed: June 8, 2006
    Publication date: December 13, 2007
    Applicant: PORTAL PLAYER, INC.
    Inventors: Rohit Puri, Parthasarathy Sriram
  • Publication number: 20070268166
    Abstract: Systems and methods for optimizing system performance in variable length decoding systems are described. Embodiments are described in which decode tables are analyzed and elements of the tables sorted by probability of occurrence. Storage of elements can be determined by probability of occurrence and embodiments of the present invention can optimize system efficiency by storing most likely entries into fast-memory and least likely entries in slowest memory. In certain embodiments, a single large table is provided that cannot fit into decoder fast-memory. In some embodiments, individual elements can be optimized for storage in fast-memory by selecting more frequently occurring entries or groups of entries into decoder memory.
    Type: Application
    Filed: May 19, 2006
    Publication date: November 22, 2007
    Applicant: PortalPlayer, Inc.
    Inventors: Rohit Puri, Partha Sriram
  • Publication number: 20050117638
    Abstract: A method and apparatus for encoding video frames is described. In one embodiment, an encoding method includes jointly transforming a set of pixels into high-pass data using an orthonormal transform. The set of pixels includes at least one reference pixel and predicted pixels. The method further includes generating low-pass data using the reference pixel and the high-pass data.
    Type: Application
    Filed: October 22, 2004
    Publication date: June 2, 2005
    Inventors: Deepak Turaga, Rohit Puri, Ali Tabatabai
  • Publication number: 20050117639
    Abstract: A method and apparatus for encoding video frames is described. In one embodiment, an encoding method includes identifying a set of similar pixels that includes at least one reference pixel and multiple predicted pixels, and jointly transforming the set of similar pixels into a set of coefficients using an orthonormal transform.
    Type: Application
    Filed: October 22, 2004
    Publication date: June 2, 2005
    Inventors: Deepak Turaga, Rohit Puri, Ali Tabatabai
  • Publication number: 20050031219
    Abstract: Encoding digital data by using cues at a decoder. An encoder selects an index to indicate a target codeword from the complete space of all codewords to a decoder. The index identifies a group or a set of codewords that contain the target codeword. The sets are represented by a bit-length that is smaller than the code word bit-length thus achieving compression. Two or more codewords in such a set are separated by a predetermined distance and all such sets of codewords considered together form the complete space of all codewords. The encoder sends syntax information, including the index, to specify the decoding. The decoder then uses a set of candidate cues in a comparison operation to determine the target codeword from the indexed set. Processing complexity can be allocated among the encoder, decoder and other possible devices as, for example, in a digital network.
    Type: Application
    Filed: August 29, 2003
    Publication date: February 10, 2005
    Applicant: The Regents of the University of California
    Inventors: Rohit Puri, Kannan Ramchandran
  • Publication number: 20050031035
    Abstract: A motion estimation method and apparatus for video coding of a multi-view sequence is described. In one embodiment, a motion estimation method includes identifying one or more pixels in a first frame of a multi-view video sequence, and constraining a search range associated with a second frame of the multi-view video sequence based on an indication of a desired correlation between efficient coding and semantic accuracy. The semantic accuracy relies on use of geometric configurations of cameras capturing the multi-view video sequence. The method further includes searching the second frame within the constrained search range for a match of the pixels identified in the first frame.
    Type: Application
    Filed: March 31, 2004
    Publication date: February 10, 2005
    Inventors: Sundar Vedula, Rohit Puri, Ali Tabatabai