Patents by Inventor Marta Karczewicz

Marta Karczewicz 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: 12293554
    Abstract: A method comprises: for each of a plurality of dimensions: identifying a reference position for the dimension, the reference position for the dimension being a position in a reference frame for the respective dimension, and the reference frame for the respective dimension and a reference frame for at least one other dimension in the plurality of dimensions being different reference frames in a plurality of reference frames; identifying an inter predictor for the respective dimension, wherein a predictor has a coordinate value in the respective dimension corresponding to a coordinate value in the respective dimension of the inter predictor for the respective dimension; and encoding or decoding the current point based on the predictor.
    Type: Grant
    Filed: January 17, 2023
    Date of Patent: May 6, 2025
    Assignee: QUALCOMM Incorporated
    Inventors: Adarsh Krishnan Ramasubramonian, Geert Van der Auwera, Luong Pham Van, Marta Karczewicz
  • Patent number: 12284386
    Abstract: A method of decoding video data comprises updating a coefficient statistic value based on one or more transform coefficients of a transform block (TB), wherein updating the coefficient statistic value comprises, for each respective transform coefficient of the one or more transform coefficients of the TB: performing a derivation process to determine a temporary value, wherein the derivation process is determined based at least in part on which encoding procedure of a plurality of encoding procedures is used to encode the respective transform coefficient, the plurality of encoding procedures including a context-based procedure for encoding the respective transform coefficient and encoding the respective transform coefficient as an absolute value; and setting the coefficient statistic value as an average of the coefficient statistic value and the temporary value; determining a history value based on the coefficient statistic value; determining a Rice parameter for a specific transform coefficient of the TB.
    Type: Grant
    Filed: June 29, 2023
    Date of Patent: April 22, 2025
    Assignee: QUALCOMM Incorporated
    Inventors: Dmytro Rusanovskyy, Marta Karczewicz
  • Patent number: 12283074
    Abstract: A device for encoding point cloud data, the device comprising: a memory to store the point cloud data; and one or more processors coupled to the memory and implemented in circuitry, the one or more processors configured to: determine a horizontal plane position of a node, wherein the horizontal plane position indicates a position of a single plane that is perpendicular to a first axis of a coordinate system, wherein the first axis is a horizontal axis; determine, from a plurality of contexts consisting of 8 contexts, a context for the horizontal plane position of the node; and perform arithmetic encoding on a syntax element indicating the horizontal plane position using the determined context.
    Type: Grant
    Filed: April 4, 2024
    Date of Patent: April 22, 2025
    Assignee: QUALCOMM INCORPORATED
    Inventors: Geert Van der Auwera, Bappaditya Ray, Adarsh Krishnan Ramasubramonian, Marta Karczewicz
  • Patent number: 12283073
    Abstract: An example of processing a point cloud includes responsive to determining to predict a current point in the point cloud using predictive geometry coding, selecting, from a set of prediction modes, a prediction mode for the current point, wherein the set of prediction modes includes at least an intra prediction mode and an inter prediction mode; and responsive to selecting the inter prediction mode for the current point, predicting the current point of the point cloud using inter prediction.
    Type: Grant
    Filed: December 28, 2021
    Date of Patent: April 22, 2025
    Assignee: QUALCOMM Incorporated
    Inventors: Adarsh Krishnan Ramasubramonian, Bappaditya Ray, Luong Pham Van, Geert Van der Auwera, Marta Karczewicz
  • Publication number: 20250126293
    Abstract: A device for decoding point cloud data includes: one or more memories configured to store the point cloud data; and processing circuitry coupled to the one or more memories, wherein the processing circuitry is configured to: apply a first process to a reference point cloud frame to generate a first level processed frame; apply a second process to the first level processed frame to generate a second level processed frame; inter-prediction decode geometry data of points of a current point cloud frame using the first level processed frame; and inter-prediction decode attribute data of points of the current point cloud frame using the second level processed frame.
    Type: Application
    Filed: October 10, 2024
    Publication date: April 17, 2025
    Inventors: Adarsh Krishnan Ramasubramonian, Geert Van der Auwera, Marta Karczewicz
  • Publication number: 20250126241
    Abstract: A video coder configured to receive a block of video data to be coded using merge mode and local illumination compensation (LIC), and determine a merge candidate for the block of video data. If the merge candidate is a non-adjacent candidate or a history-based motion vector predictor candidate, the video coder is configured to inherit LIC parameters associated with the merge candidate. If the merge candidate is an adjacent candidate, the video coder is configured to derive LIC parameters for the block of video data using a neighboring template of reconstructed samples and a reference template in a reference frame.
    Type: Application
    Filed: September 13, 2024
    Publication date: April 17, 2025
    Inventors: Han Huang, Vadim Seregin, Marta Karczewicz
  • Patent number: 12278986
    Abstract: An example device includes memory configured to store the video data and one or more processors implemented in circuitry and communicatively coupled to the memory. The one or more processors are configured to determine at least one of a temporal candidate or a history-based candidate and determine at least one non-adjacent candidate, wherein the at least one non-adjacent candidate is from a unit that is not adjacent to a current prediction unit (PU). The one or more processors are configured to determine an advanced motion vector predictor (AMVP) candidate list including the at least one of the temporal candidate or the history-based candidate and the at least one non-adjacent candidate. The at least one non-adjacent candidate is added to the AMVP candidate list after the temporal candidate or before the history-based candidate. The one or more processors are configured to code the current PU based on the AMVP candidate list.
    Type: Grant
    Filed: November 20, 2023
    Date of Patent: April 15, 2025
    Assignee: QUALCOMM Incorporated
    Inventors: Yan Zhang, Zhi Zhang, Vadim Seregin, Marta Karczewicz, Chun-Chi Chen
  • Publication number: 20250119528
    Abstract: A device for decoding encoded video data is configured to determine that a chroma block of the encoded video data is coded in a cross-component prediction (CCP) mode; generate a merge candidate list for the chroma block, wherein the merge candidate list includes at least two prediction candidates generated by different CCP modes and a third prediction candidate, wherein the third prediction candidate comprises a fusion prediction candidate; receive, in the encoded video data, a syntax element set to a value; select a prediction candidate from the merge candidate list based on the value of the syntax element; determine a prediction block for the chroma block based on the selected prediction candidate; determine a decoded block of video data based on the prediction block for the chroma block; and output a decoded picture of video data that includes the decoded block of video data.
    Type: Application
    Filed: October 2, 2024
    Publication date: April 10, 2025
    Inventors: Po-Han Lin, Jian-Liang Lin, Yao-Jen Chang, Vadim Seregin, Marta Karczewicz
  • Publication number: 20250119527
    Abstract: Example devices, methods, and computer-readable media are disclosed for decoding video data. An example method includes determining to decode a current block of the video data using a merge mode. The example method includes obtaining a flag from a bitstream. The example method includes determining, based on a value of the flag, to use a second merge list of two merge lists for the current block, wherein the second merge list is based on a first merge list of the two merge lists. The example method includes decoding the current block based on the second merge list.
    Type: Application
    Filed: September 11, 2024
    Publication date: April 10, 2025
    Inventors: Yan Zhang, Vadim Seregin, Hongtao Wang, Zhi Zhang, Chun-Chi Chen, Han Huang, Marta Karczewicz
  • Publication number: 20250119556
    Abstract: A method of processing video data includes receiving a picture; and filtering a current block of the picture, through a neural network and based on local correlations of proximate samples and distant, non-local correlations of non-proximate samples relative to the current block, to generate a filtered current block. The neural network comprises one or more backbone blocks and one or more transformer blocks. Each of the one or more transformer blocks is associated with a backbone block of the one or more backbone blocks. At least one of the backbone blocks is configured to capture the local correlations, relative to the current block and the proximate samples of the current block, and at least one of the transformer blocks is configured to generate features, based on applying an attention mechanism, that capture the distant, non-local correlations, relative to the current block and the non-proximate samples, in the picture for processing.
    Type: Application
    Filed: September 19, 2024
    Publication date: April 10, 2025
    Inventors: Yun Li, Dmytro Rusanovskyy, Thomas Alexander Ryder, Samuel James Eadie, Marta Karczewicz
  • Publication number: 20250119529
    Abstract: Systems and techniques are provided for overlapped block motion compensation (OBMC). A method can include determining an OBMC mode is enabled for a current subblock of video data; for a neighboring subblock(s) adjacent to the current subblock, determining whether a first, second and third condition are met, the first condition comprising that all reference picture lists for predicting the current subblock are used to predict the neighboring subblock; the second condition comprising that identical reference pictures are used to determine motion vectors associated with the current subblock and the neighboring subblock, and the third condition comprising that a difference between motion vectors of the current subblock and the neighboring subblock do not exceed a threshold; and based on determining that the OBMC mode is enabled and the first, second, and third conditions are met, determining not to use motion information of the neighboring subblock for motion compensation of the current subblock.
    Type: Application
    Filed: November 1, 2024
    Publication date: April 10, 2025
    Inventors: Yao-Jen CHANG, Jingya LI, Vadim SEREGIN, Marta KARCZEWICZ
  • Publication number: 20250119539
    Abstract: A video coder may receive video data, and apply a filter to a plurality of categories of samples of the video data. The plurality of categories of samples may include two or more of an input of a fixed filter, an output of the fixed filter, an input of a signaled filter, an output of the signaled filter, an input of an adaptive loop filter, an output of the adaptive loop filter, an input of a sample adaptive offset (SAO) filter, an output of the SAO filter, an input of a bilateral filter, an output of the bilateral filter, an input of a cross component SAO filter, an output of the cross component SAO filter, an input of a deblocking filter, an output of the deblocking filter, filtered reconstructed residual data, dequantized coefficients, filtered dequantized coefficients, a predictor, or a filtered predictor.
    Type: Application
    Filed: September 6, 2024
    Publication date: April 10, 2025
    Inventors: Nan Hu, Marta Karczewicz, Vadim Seregin
  • Publication number: 20250119540
    Abstract: A device for filtering decoded video data includes a memory configured to store video data; and a processing system implemented in circuitry and configured to: calculate a filter selection value for a decoded block of video data; quantize the filter selection value using a scaling factor to form a quantized filter selection value; select a filter for the decoded block according to the quantized filter selection value; and filter the decoded block using the selected filter. The filter selection value may be an activity value that is the sum of horizontal and vertical Laplacian values. The processing system may quantize the filter selection value using a scaling factor, which the processing system may determine based on a color component to which the block belongs and/or a color sampling format of a picture including the block.
    Type: Application
    Filed: September 11, 2024
    Publication date: April 10, 2025
    Inventors: Nan Hu, Marta Karczewicz, Vadim Seregin
  • Publication number: 20250119581
    Abstract: A device for decoding encoded mesh data is configured to receive, in a bitstream of the encoded mesh data, one or more syntax elements; determine an offset value based on the one or more syntax elements; determine a set of transform coefficients; apply the offset to the set of transform coefficients to determine a set of updated transform coefficients; inverse transform the set of updated transform coefficients to determine a set of displacement vectors; and determine a decoded mesh based on the set of displacement vectors.
    Type: Application
    Filed: September 11, 2024
    Publication date: April 10, 2025
    Inventors: Reetu Hooda, Geert Van der Auwera, Anique Akhtar, Adarsh Krishnan Ramasubramonian, Marta Karczewicz
  • Publication number: 20250119547
    Abstract: A video decoder is configured to determine a minimum sample value for one or more blocks of video data, the minimum sample value being greater than 0; determine a maximum sample value for the one or more blocks of video data, the maximum sample value being less than 2{circumflex over (?)}bd?1 and bd being a bit depth of samples in the one or more blocks; in response to determining that a process applied to a block of the one or more blocks of video data results in a sample value that is outside a range of the minimum sample value to the maximum sample value, clip the sample value to one of the minimum sample value or the maximum sample value to generate a clipped sample value; determine a decoded version of the block based on the clipped sample value.
    Type: Application
    Filed: September 12, 2024
    Publication date: April 10, 2025
    Inventors: Kai Cui, Zhi Zhang, Han Huang, Vadim Seregin, Marta Karczewicz
  • Publication number: 20250119565
    Abstract: Example devices, methods, and computer-readable media for decoding video data are described. An example method includes determining to decode a current block of the video data using a merge mode. The example method includes generating a first merge list for the current block, wherein generating the first merge list comprises applying template matching to candidates of the first merge list. The example method includes generating, based on the first merge list, a second merge list. The example method includes decoding the current block using the merge mode and based on the first merge list or the second merge list.
    Type: Application
    Filed: September 11, 2024
    Publication date: April 10, 2025
    Inventors: Yan Zhang, Vadim Seregin, Hongtao Wang, Zhi Zhang, Chun-Chi Chen, Han Huang, Marta Karczewicz
  • Publication number: 20250119536
    Abstract: A video decoder may be configured to receive a first instance of a flag for a first block, with a first value for the flag indicating that a cross-component prediction (CCP) mode is derived without signaling and a second value for the flag indicating that the CCP mode is signaled; in response to determining that the first instance of the flag is set to the first value, derive a first CCP mode for the first block; determine a first predicted chroma block for the first block using the first CCP mode; determine a decoded version of the first block based on the first predicted chroma block; and output a picture of decoded video data that includes the decoded version of the first block.
    Type: Application
    Filed: September 20, 2024
    Publication date: April 10, 2025
    Inventors: Yao-Jen Chang, Po-Han Lin, Vadim Seregin, Jian-Liang Lin, Marta Karczewicz
  • Publication number: 20250119535
    Abstract: Example devices, methods, and computer-readable media are described. An example method includes determining to decode a current block of the video data using a merge mode. The example method includes determining, for the current block, to apply local illumination compensation (LIC). The example method includes determining, for the current block, to apply decoder side motion vector refinement (DMVR). The example method includes decoding the current block based on applying LIC and applying DMVR.
    Type: Application
    Filed: September 11, 2024
    Publication date: April 10, 2025
    Inventors: Yan Zhang, Vadim Seregin, Hongtao Wang, Zhi Zhang, Chun-Chi Chen, Han Huang, Marta Karczewicz
  • Publication number: 20250119548
    Abstract: A method of encoding or decoding video data comprises: for each respective intra prediction mode of a plurality of intra prediction modes in a most-probable mode (MPM) list: generating, based on reference samples for a template region and using the respective intra prediction mode, prediction samples for the template region; and determining a cost for the respective intra prediction mode; determining a first intra prediction mode and a second intra prediction mode in the MPM list having lowest costs; determining a preliminary prediction block for the first intra prediction mode and a preliminary prediction block for the second intra prediction mode; generating a prediction block based on a fusion of the preliminary prediction blocks weighted according to a weight for the first intra prediction mode and a weight for the second intra prediction mode.
    Type: Application
    Filed: December 16, 2024
    Publication date: April 10, 2025
    Inventors: Keming Cao, Nan Hu, Vadim Seregin, Marta Karczewicz
  • Publication number: 20250119592
    Abstract: Methods and devices for decoding video data are described. An example method includes in-loop filtering a current block of the video data using a neural network-based in-loop filter to generate an in-loop filtered current block, wherein the neural network-based in-loop filter is trained using an architecture comprising a U-Net architecture comprising one or more residual blocks and one or more transform blocks; and outputting the in-loop filtered current block.
    Type: Application
    Filed: September 18, 2024
    Publication date: April 10, 2025
    Inventors: Thomas Alexander Ryder, Dmytro Rusanovskyy, Samuel James Eadie, Yun Li, Marta Karczewicz