公开(公告)号：US12283073B2

公开(公告)日：2025-04-22

申请号：US17646217

申请日：2021-12-28

Applicant: QUALCOMM Incorporated

Inventor： Adarsh Krishnan Ramasubramonian ,  Bappaditya Ray ,  Luong Pham Van ,  Geert Van der Auwera ,  Marta Karczewicz

IPC: G06T9/00 ,  H04N19/105 ,  H04N19/107 ,  H04N19/169 ,  H04N19/172 ,  H04N19/597 ,  H04N19/70

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.

公开(公告)号：US20250126293A1

公开(公告)日：2025-04-17

申请号：US18911872

申请日：2024-10-10

Applicant: QUALCOMM Incorporated

Inventor： Adarsh Krishnan Ramasubramonian ,  Geert Van der Auwera ,  Marta Karczewicz

IPC: H04N19/597 ,  H04N19/159 ,  H04N19/172 ,  H04N19/423

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.

公开(公告)号：US20250126241A1

公开(公告)日：2025-04-17

申请号：US18884960

申请日：2024-09-13

Applicant: QUALCOMM Incorporated

Inventor： Han Huang ,  Vadim Seregin ,  Marta Karczewicz

IPC: H04N19/105 ,  H04N19/124 ,  H04N19/132 ,  H04N19/139 ,  H04N19/159 ,  H04N19/176 ,  H04N19/463 ,  H04N19/52

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.

公开(公告)号：US12278986B2

公开(公告)日：2025-04-15

申请号：US18514588

申请日：2023-11-20

Applicant: QUALCOMM Incorporated

Inventor： Yan Zhang ,  Zhi Zhang ,  Vadim Seregin ,  Marta Karczewicz ,  Chun-Chi Chen

IPC: H04N19/52 ,  H04N19/105 ,  H04N19/55 ,  H04N19/70 ,  H04N19/176

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.

公开(公告)号：US12231666B2

公开(公告)日：2025-02-18

申请号：US17643383

申请日：2021-12-08

Applicant: QUALCOMM Incorporated

Inventor： Hilmi Enes Egilmez ,  Ankitesh Kumar Singh ,  Muhammed Zeyd Coban ,  Marta Karczewicz

IPC: H04N19/42 ,  G06N3/048 ,  H04N19/124 ,  H04N19/172 ,  H04N19/186 ,  H04N19/91 ,  G06N3/045

Abstract: Techniques are described herein for processing video data using a neural network system. For instance, a process can include generating, by a first convolutional layer of an encoder sub-network of the neural network system, output values associated with a luminance channel of a frame. The process can include generating, by a second convolutional layer of the encoder sub-network, output values associated with at least one chrominance channel of the frame. The process can include generating, by a third convolutional layer based on the output values associated with the luminance channel of the frame and the output values associated with the at least one chrominance channel of the frame, a combined representation of the frame. The process can further include generating encoded video data based on the combined representation of the frame.

公开(公告)号：US20250039433A1

公开(公告)日：2025-01-30

申请号：US18764869

申请日：2024-07-05

Applicant: QUALCOMM Incorporated

Inventor： Luong Pham Van ,  Wei-Jung Chien ,  Vadim Seregin ,  Marta Karczewicz ,  Han Huang

IPC: H04N19/52 ,  H04N19/15 ,  H04N19/513 ,  H04N19/615

Abstract: An example device for coding video data includes a memory configured to store video data; and one or more processing units implemented in circuitry and configured to: store motion information for a first coding tree unit (CTU) line of a picture in a first history motion vector predictor (MVP) buffer of the memory; reset a second history MVP buffer of the memory; and after resetting the second history MVP buffer, store motion information for a second CTU line of the picture in the second history MVP buffer, the second CTU line being different than the first CTU line. Separate threads of a video coding process executed by the one or more processors may process respective CTU lines, in some examples.

公开(公告)号：US12192469B2

公开(公告)日：2025-01-07

申请号：US17804972

申请日：2022-06-01

Applicant: QUALCOMM Incorporated

Inventor： Keming Cao ,  Nan Hu ,  Vadim Seregin ,  Marta Karczewicz

IPC: H04N11/02 ,  H04N19/105 ,  H04N19/132 ,  H04N19/146 ,  H04N19/159 ,  H04N19/176

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.

公开(公告)号：US12177475B2

公开(公告)日：2024-12-24

申请号：US17586492

申请日：2022-01-27

Applicant: QUALCOMM Incorporated

Inventor： Chun-Chi Chen ,  Han Huang ,  Vadim Seregin ,  Marta Karczewicz

IPC: H04N19/523 ,  H04N19/105 ,  H04N19/139 ,  H04N19/176 ,  H04N19/513

Abstract: An example device for decoding video data includes a memory configured to store video data; and one or more processors configured to: decode data representing an initial motion vector for a current block of the video data, the initial motion vector having integer-motion vector difference (MVD) precision; determine a search range around a reference area identified by the initial motion vector in a reference picture; perform a template matching search process in the search range to identify a best matching region; determine error values for neighboring pixels to the best matching region; use the error values for the neighboring pixels to perform a model-based fractional-pixel motion vector refinement to derive motion vector difference values; apply at least one of the motion vector difference values to the initial motion vector to determine a refined motion vector for the current block; and decode the current block using the refined motion vector.

公开(公告)号：US20240414339A1

公开(公告)日：2024-12-12

申请号：US18734509

申请日：2024-06-05

Applicant: QUALCOMM Incorporated

Inventor： Marta Karczewicz ,  Muhammed Zeyd Coban ,  Pavel Nikitin

IPC: H04N19/124 ,  H04N19/176 ,  H04N19/186 ,  H04N19/50

Abstract: A method of processing video data includes determining a quantization level for a coefficient of a current block from a plurality of quantization levels; determining an offset value based on the quantization level, wherein the offset value is a first offset value based on the quantization level being a first quantization level or a second, different offset value based on the quantization level being a second quantization level; determining a quantization parameter or an inverse-quantization parameter for the coefficient based on the determined offset value; and as part of encoding or decoding the current block, performing one of quantization or inverse-quantization for the coefficient based on the determined quantization parameter or the determined inverse-quantization parameter.

公开(公告)号：US20240414333A1

公开(公告)日：2024-12-12

申请号：US18734814

申请日：2024-06-05

Applicant: QUALCOMM Incorporated

Inventor： Ikram Jumakulyyev ,  Nan Hu ,  Vadim Seregin ,  Marta Karczewicz

IPC: H04N19/117 ,  H04N19/124 ,  H04N19/159 ,  H04N19/174 ,  H04N19/176 ,  H04N19/186 ,  H04N19/70 ,  H04N19/82 ,  H04N19/86

Abstract: A device for decoding video data, as part of applying a first stage of an adaptive loop filter (ALF) to a reconstructed sample of a reconstructed block for a color component, selects a first set of filters from a plurality of sets of fixed filters based on a quantization parameter of the block of video data and a second characteristic of the block of video data; determines a first class index for the reconstructed sample; selects a filter from a first set of filters based on the first class index; and applies the filter from the first set of filters to the reconstructed sample to determine a first intermediate sample value.