Patents by Inventor Madhu Peringassery Krishnan

Madhu Peringassery Krishnan 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: 20250113031
    Abstract: A method of video decoding includes receiving a bitstream that comprises coded information of a current block, the coded information of the current block includes coded bits of quantized transform coefficients in a transform domain of the current block, the coded information is also indicative of at least a scaling factor to be used during a dequantization of the quantized transform coefficients. The method also includes determining one or more quantization shifting offsets for a reconstruction of transform coefficients in the transform domain based on at least the scaling factor, reconstructing the transform coefficients from the quantized transform coefficients based on the one or more quantization shifting offsets, calculating residuals in a spatial domain of the current block based on the transform coefficients in the transform domain, and reconstructing the current block according to the residuals in the spatial domain.
    Type: Application
    Filed: September 25, 2024
    Publication date: April 3, 2025
    Applicant: Tencent America LLC
    Inventors: Motong XU, Roman CHERNYAK, Xin ZHAO, Madhu PERINGASSERY KRISHNAN, Biao WANG, Lien-Fei CHEN, Yonguk YOON, Shan LIU
  • Publication number: 20250106404
    Abstract: This disclosure relates generally to video coding and particularly to methods, devices, and systems for signaling prediction modes in recursively partitioned video frames. For example, a regional prediction mode flag syntax element may be introduced for indicating whether an entire coding region of a video frame signaled as being of a first predefined prediction mode is entirely coded in a second predefined prediction mode or not. The signaling schemes described in this disclosure facilitate reducing signaling overhead in video frames that employ a mix of different prediction modes.
    Type: Application
    Filed: April 11, 2024
    Publication date: March 27, 2025
    Applicant: TENCENT AMERICA LLC
    Inventors: Liang ZHAO, Xin ZHAO, Han GAO, Jing YE, Madhu PERINGASSERY KRISHNAN, Yushin CHO, Shan LIU
  • Publication number: 20250106392
    Abstract: Some aspects of the disclosure provide a method of video decoding. The method includes: receiving a bitstream that comprises coded information of one or more pictures; generating, according to the bitstream, at least a to-be-filtered sample, and input samples for filtering the to-be-filtered sample in an in-loop filter, the in-loop filter using a Wiener-based filter with an adaptive filter shape; determining a modified filter shape for the Wiener-based filter, the modified filter shape being adapted according to a relationship between the to-be-filtered sample and the input samples; and applying the Wiener-based filter with the modified filter shape on the input samples to generate a filtered output of the to-be-filtered sample.
    Type: Application
    Filed: September 23, 2024
    Publication date: March 27, 2025
    Applicant: Tencent America LLC
    Inventors: Han ZHANG, Roman CHERNYAK, Lien-Fei CHEN, Madhu PERINGASSERY KRISHNAN, Biao WANG, Xin ZHAO, Motong XU, Yonguk YOON, Shan LIU
  • Patent number: 12256077
    Abstract: The various embodiments described herein include methods and systems for coding video. In one aspect, a method includes obtaining video data including a syntax element with a corresponding alphabet of M elements, a first set of respective probabilities of occurrence for the M elements of the syntax element; and a second set of respective probabilities of occurrence for the M elements of the syntax element. The method further includes entropy coding a first portion of the video data in accordance with an aggregation of the first and second sets; and, while entropy coding the first portion of the video data, encountering a first syntax element. The method also includes updating the first set at a first rate and updating the second set at a second rate, faster than the first rate. The method further includes adaptively entropy coding a second portion of the video data.
    Type: Grant
    Filed: March 14, 2023
    Date of Patent: March 18, 2025
    Assignee: TENCENT AMERICA LLC
    Inventors: Madhu Peringassery Krishnan, Xin Zhao, Shan Liu
  • Publication number: 20250061717
    Abstract: The various implementations described herein include methods and systems for coding video. In one aspect, a method includes receiving a video bitstream that includes encoded video data; obtaining information indicating two or more different clipping ranges for the encoded video data; deriving the two or more different clipping ranges based on the obtained information; performing a first clipping operation on a first portion of the encoded video data based on a first clipping range of the two or more different clipping ranges; and performing a second clipping operation on a second portion of the encoded video data based on a second clipping range different from the first clipping range.
    Type: Application
    Filed: November 4, 2023
    Publication date: February 20, 2025
    Inventors: Roman CHERNYAK, Biao WANG, Xin ZHAO, Lien-Fei CHEN, Madhu PERINGASSERY KRISHNAN, Shan LIU
  • Publication number: 20250063170
    Abstract: This disclosure relates generally to video coding/decoding and particularly for a transform dictionary. A method includes receiving the coded video bitstream; determining, based on the coded video bitstream, a transform pile for the current block, the transform pile being one transform pile in a transform dictionary, the transform dictionary comprising a plurality of transform piles, and the transform pile comprising a plurality of transform sets; determining a transform set in the transform pile; determining a transform kernel in the transform set; performing an inverse transform for the current block based on the transform kernel for obtaining a residual block for the current block; and reconstructing the current block based on the residual block.
    Type: Application
    Filed: November 28, 2023
    Publication date: February 20, 2025
    Applicant: Tencent America LLC
    Inventors: Xin ZHAO, Yushin CHO, Madhu PERINGASSERY KRISHNAN, Liang ZHAO, Han GAO, Jing YE, Shan LIU
  • Publication number: 20250063172
    Abstract: The various implementations described herein include methods and systems for coding video. In one aspect, a method includes receiving a video bitstream that includes encoded video data and one or more syntax elements indicating one or more clipping ranges. The method includes deriving, based on the one or more syntax elements, the one or more clipping ranges for a portion of the encoded video data. Each of the one or more clipping ranges modifies a range of sample values of the received video bitstream. The method includes performing one or more clipping operations on the encoded video data using the derived one or more clipping ranges.
    Type: Application
    Filed: November 4, 2023
    Publication date: February 20, 2025
    Inventors: Roman CHERNYAK, Biao WANG, Xin ZHAO, Lien-Fei CHEN, Madhu PERINGASSERY KRISHNAN, Shan LIU
  • Publication number: 20250047849
    Abstract: Methods and systems for encoding and decoding video are described. In one aspect, a method of video decoding includes receiving video data that includes a first block and a first syntax element from a video bitstream. The method also includes determining a secondary transform kernel type value for the first block based on the first syntax element. In accordance with a determination that the secondary transform kernel type has a first value, a secondary transform set identifier is determined based on a second syntax element from the video bitstream, and an inverse secondary transform is performed on the first block using the determined secondary transform kernel type and determined secondary transform set identifier. In accordance with a determination that the secondary transform kernel type has a second value, the inverse secondary transform is not performed on the first block.
    Type: Application
    Filed: November 27, 2023
    Publication date: February 6, 2025
    Inventors: Yushin Cho, Xin Zhao, Liang Zhao, Madhu Peringassery Krishnan, Jing Ye, Han Gao, Shan Liu
  • Publication number: 20250039385
    Abstract: This disclosure relates generally to video coding/decoding. One method includes receiving a video bitstream comprising a current picture, the current picture comprising the current block, and the current block comprising a current transform block; extracting a syntax element for a skip transform flag, the skip transform flag indicating whether the current transform block has all zero coefficient; deriving a context for entropy decoding the skip transform flag based on at least one of: a prediction mode of the current transform block; a quantization index information for the current transform block; or whether the current transform block is calculated by a secondary transform that is applied jointly on a transform block of a second component; decoding the skip transform flag using the context; and reconstructing the current block based on skip transform flag.
    Type: Application
    Filed: April 23, 2024
    Publication date: January 30, 2025
    Applicant: Tencent America LLC
    Inventors: Xin ZHAO, Madhu PERINGASSERY KRISHNAN, Jing YE, Liang ZHAO, Han GAO, Shan LIU
  • Patent number: 12206898
    Abstract: A method of decoding image data is provided. The method may include generating a dequantized block of an image based on a coded bitstream; determining whether to use one from among an implicit method and an explicit method for selecting a hybrid transform kernel from among one or more hybrid transform kernel that are available for decoding the dequantized block, wherein the one or more hybrid transform kernel are available for decoding the dequantized block based on associations between prediction modes and sizes of blocks; selecting, by using the one from among the implicit method and the explicit method, the hybrid transform kernel from among the one or more hybrid transform kernel; and performing inverse transform coding of the dequantized block based on the selected hybrid transform kernel.
    Type: Grant
    Filed: November 10, 2023
    Date of Patent: January 21, 2025
    Assignee: TENCENT AMERICA LLC
    Inventors: Madhu Peringassery Krishnan, Xin Zhao, Shan Liu
  • Patent number: 12206855
    Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding and decoding. Processing circuitry of an apparatus for video decoding decodes coded information for one or more blocks from a coded video bitstream. The coded information indicates whether to apply a super resolution coding mode to the one or more blocks. The super resolution coding mode is applied in response to the one or more blocks having been down sampled from a high spatial resolution to a low spatial resolution lower than the high spatial resolution by an encoder. Based on the coded information indicating that the super resolution coding mode is applied to the one or more blocks, the processing circuitry can generate, using the super resolution coding mode, a reconstructed block having the high spatial resolution by upsampling information of a first block having the low spatial resolution in the one or more blocks including transform coefficients.
    Type: Grant
    Filed: September 22, 2021
    Date of Patent: January 21, 2025
    Assignee: Tencent America LLC
    Inventors: Sehoon Yea, Madhu Peringassery Krishnan, Xin Zhao, Shan Liu
  • Publication number: 20250024045
    Abstract: A method includes receiving a bitstream of coded information for a sequence of pictures, the coded information indicates an inter prediction of a current block in a current picture using a formular based inter prediction technique, the formular based inter prediction technique generates a prediction sample of the current block based on a formular with reconstructed samples of a reference block in a reference picture being input to the formular, the formular includes parameters derived based on a current template of the current block and a reference template of the reference block. The method also includes constructing a candidate list including one or more coded blocks associated with the current block, a coded block in the one or more coded blocks is a candidate that provides formular based inter prediction information.
    Type: Application
    Filed: July 11, 2024
    Publication date: January 16, 2025
    Applicant: Tencent America LLC
    Inventors: Lien-Fei CHEN, Madhu PERINGASSERY KRISHNAN, Roman CHERNYAK, Biao WANG, Xin ZHAO, Shan LIU
  • Publication number: 20250024063
    Abstract: Aspects of the disclosure includes methods and apparatuses for video decoding and video encoding and a method of processing visual media data. Coded information in a bitstream is received. The coded information indicates whether filtering is to be applied to at least one of a current template of a current block in a current picture and a reference template of a reference block. The current block is predicted based on the reference block. When the coded information indicates that the filtering is to be applied, a plurality of samples in the at least one of the current template and the reference template is filtered. A linear model between the current template and the reference template is determined based on the filtered plurality of samples. The current block is reconstructed based on the linear model and the reference block.
    Type: Application
    Filed: July 10, 2024
    Publication date: January 16, 2025
    Applicant: Tencent America LLC
    Inventors: Biao WANG, Madhu PERINGASSERY KRISHNAN, Lien-Fei CHEN, Roman CHERNYAK, Xin ZHAO, Shan LIU
  • Publication number: 20250024019
    Abstract: This disclosure relates transform configuration and signaling for a compound inter intra prediction modes. In one example, a method for decoding a video block in a video stream is disclosed. The method may include determining that the video block is predicted in a Compound Inter Intra Prediction (CIIP) mode, wherein the video block is derived as a combination of an intra prediction and an inter prediction in the CIIP mode.
    Type: Application
    Filed: September 23, 2024
    Publication date: January 16, 2025
    Applicant: TENCENT AMERICA LLC
    Inventors: Madhu PERINGASSERY KRISHNAN, Xin ZHAO, Shan LIU
  • Publication number: 20250024044
    Abstract: A method includes receiving a bitstream that includes first coded information of a current block in a current picture. The first coded information indicates an inter prediction of the current block based on a reference block in a reference picture for the current block, and a potential application of a formular based inter prediction technique on the inter prediction of the current block. The method also includes determining first formular based inter prediction information for the potential application of the formular based inter prediction technique on the current block based on at least one of the first coded information of the current block and second coded information of a second block that is reconstructed before the current block.
    Type: Application
    Filed: July 10, 2024
    Publication date: January 16, 2025
    Applicant: Tencent America LLC
    Inventors: Lien-Fei CHEN, Roman CHERNYAK, Xin ZHAO, Biao WANG, Madhu PERINGASSERY KRISHNAN, Shan LIU
  • Publication number: 20250024016
    Abstract: A method includes receiving a bitstream that includes coded information of a sequence of pictures. The coded information indicates an inter prediction of a current block in a current picture, and an adjustment factor to a linear formular that is used in a formular based inter prediction of the inter prediction. The formular based inter prediction generates a prediction sample of the current block based on a linear formular with one or more reconstructed samples in a reference block being input to the linear formular, the linear formular includes one or more parameters derived based on a current template of the current block and a reference template of the reference block. The method also includes applying the adjustment factor on the linear formular to generate an adjusted linear formular, and determining at least a reconstructed sample of the current block according to the adjusted linear formular.
    Type: Application
    Filed: July 10, 2024
    Publication date: January 16, 2025
    Applicant: Tencent America LLC
    Inventors: Lien-Fei CHEN, Roman Chernyak, Liang Zhao, Xin Zhao, Biao Wang, Madhu Peringassery Krishnan, Shan Liu
  • Publication number: 20250024031
    Abstract: Aspects of the disclosure includes methods and apparatuses for video decoding and video encoding and a method of processing visual media data. The apparatus for video decoding includes processing circuitry that receives coded information indicating that a current block in a current picture is coded with a decoder-side intra mode derivation (DIMD) mode. A template of the current block includes reconstructed samples in the current picture and is adjacent to the current block. The template includes one of a left template and a top template. The processing circuitry determines a filter type from a plurality of filter types associated with the one of the left template and the top template, applies the DIMD mode to the template based on the determined filter type to determine one or more intra prediction modes for the current block, and reconstructs the current block according to the one or more intra prediction modes.
    Type: Application
    Filed: July 10, 2024
    Publication date: January 16, 2025
    Applicant: Tencent America LLC
    Inventors: Biao WANG, Roman CHERNYAK, Xin ZHAO, Madhu PERINGASSERY KRISHNAN, Lien-Fei CHEN, Shan LIU
  • Patent number: 12200192
    Abstract: A method includes receiving a current picture, a first reference picture, and a second reference picture. The method includes obtaining a plurality of predefined weighting patterns, each weighting pattern being signaled as an index value and selecting a weighting pattern based on a predetermined condition. The method includes deriving a first weight to be applied to a first sub-block in the first reference picture and a second weight to be applied to a second sub-block in the second reference picture based on the index value corresponding to the selected weighting pattern. The method includes assigning the first weight to the first sub-block and the second weight to the second sub-block based on the selected weighting pattern. The method includes decoding the current block by a weighted bi-prediction based at least on the first sub-block weighted by the first weight and the second sub-block weighted by the second weight.
    Type: Grant
    Filed: November 3, 2022
    Date of Patent: January 14, 2025
    Assignee: TENCENT AMERICA LLC
    Inventors: Madhu Peringassery Krishnan, Xin Zhao, Liang Zhao, Han Gao, Xiaozhong Xu, Shan Liu
  • Publication number: 20250016336
    Abstract: Methods, apparatus, and computer readable storage medium for implementation of signaling EOC/EOR. The method includes determining whether a one-dimensional transform skip is applied to a transform block, the transform block having two dimensions; encoding a first syntax element indicating whether the one-dimensional transform skip is applied to the transform block; in response to the one-dimensional transform skip being applied to the transform block, encoding a second syntax element indicating an end position value associated with the transform block, the end position value indicating only one of a horizontal coordinate end position in the transform block and a vertical coordinate end position in the transform block; entropy encoding the transform block; and transmitting a video bitstream comprising the transform block, the first syntax element, and the second syntax element.
    Type: Application
    Filed: September 23, 2024
    Publication date: January 9, 2025
    Applicant: Tencent America LLC
    Inventors: Xin ZHAO, Madhu Peringassery Krishnan, Shan Liu
  • Patent number: 12192527
    Abstract: Methods, apparatus, and computer readable storage medium for encoding/decoding video data in a decoder. The method includes receiving a first End of Block (EOB) flag associated with a first color component of a data block from the video data; deriving a context for entropy encoding the first EOB flag based on a second EOB flag associated with a second color component of the data block of the video data; and performing entropy decoding of the first EOB flag based on the derived context.
    Type: Grant
    Filed: January 14, 2022
    Date of Patent: January 7, 2025
    Assignee: TENCENT AMERICA LLC
    Inventors: Xin Zhao, Madhu Peringassery Krishnan, Shan Liu