公开(公告)号：US20250119565A1

公开(公告)日：2025-04-10

申请号：US18882254

申请日：2024-09-11

Applicant: QUALCOMM Incorporated

Inventor： Yan Zhang ,  Vadim Seregin ,  Hongtao Wang ,  Zhi Zhang ,  Chun-Chi Chen ,  Han Huang ,  Marta Karczewicz

IPC: H04N19/44 ,  H04N19/105 ,  H04N19/176

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.

公开(公告)号：US20250119535A1

公开(公告)日：2025-04-10

申请号：US18882291

申请日：2024-09-11

Applicant: QUALCOMM Incorporated

Inventor： Yan Zhang ,  Vadim Seregin ,  Hongtao Wang ,  Zhi Zhang ,  Chun-Chi Chen ,  Han Huang ,  Marta Karczewicz

IPC: H04N19/109 ,  H04N19/176 ,  H04N19/44 ,  H04N19/463 ,  H04N19/513 ,  H04N19/573

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.

公开(公告)号：US12022095B2

公开(公告)日：2024-06-25

申请号：US16800864

申请日：2020-02-25

Applicant: QUALCOMM Incorporated

Inventor： Hongtao Wang ,  Wei-Jung Chien ,  Vadim Seregin ,  Marta Karczewicz

IPC: H04N7/12 ,  H04N19/105 ,  H04N19/117 ,  H04N19/132 ,  H04N19/159 ,  H04N19/176 ,  H04N19/182 ,  H04N19/186 ,  H04N19/51 ,  H04N19/86

CPC classification number: H04N19/186 ,  H04N19/105 ,  H04N19/117 ,  H04N19/132 ,  H04N19/159 ,  H04N19/176 ,  H04N19/182 ,  H04N19/51 ,  H04N19/86

Abstract: A device for processing video data includes a memory configured to store video data and one or more processors implemented in circuitry. The one or more processors are configured to obtain unfiltered reference samples for an area of a picture of the video data. The one or more processors are configured to disable intra-reference sample smoothing of the unfiltered reference samples for chroma samples in a YUV 4:2:0 format and in a YUV 4:4:4 format. The one or more processors are further configured to generate, using intra-prediction, chroma samples of a predicted block for a block of the picture based on the unfiltered reference samples when generating the chroma components in the YUV 4:2:0 format and when generating the chroma components in the YUV 4:4:4 format.

公开(公告)号：US20240015284A1

公开(公告)日：2024-01-11

申请号：US18346620

申请日：2023-07-03

Applicant: QUALCOMM Incorporated

Inventor： Hongtao Wang ,  Samuel James Eadie ,  Muhammed Zeyd Coban ,  Marta Karczewicz

IPC: H04N19/117 ,  H04N19/80 ,  H04N19/176

CPC classification number: H04N19/117 ,  H04N19/80 ,  H04N19/176

Abstract: An example device for filtering video data includes a memory configured to store video data; and a processing system comprising one or more processors implemented in circuitry, the processing system being configured to: apply one or more neural network processing blocks to intermediate filtered video data, each of the neural network processing blocks including a first 1×1 convolutional filter, a parametric rectified linear unit (PReLU) filter, a second 1×1 convolutional filter, and a 3×3 convolutional filter; apply additional neural network processing blocks to output of the one or more neural network processing blocks to form filtered video data; and output the filtered video data.

公开(公告)号：US11722675B2

公开(公告)日：2023-08-08

申请号：US17645439

申请日：2021-12-21

Applicant: QUALCOMM Incorporated

Inventor： Hongtao Wang ,  Jianle Chen ,  Marta Karczewicz

IPC: H04N19/186 ,  H04N19/46 ,  H04N19/146 ,  H04N19/176

CPC classification number: H04N19/146 ,  H04N19/176 ,  H04N19/186 ,  H04N19/46

Abstract: An example method includes predicting, based on a plurality of color components of a block of video data coded using joint coding of chroma residuals (JCCR), a sign of a coefficient of a plurality of coefficients of a joint residual block of the block of video data; generating, for each respective color component of the plurality of color components and based on the plurality of coefficients of the joint residual block, coefficients of a respective residual block of a plurality of residual blocks; and reconstructing, based on the plurality of residual blocks, the block of video data.

公开(公告)号：US20230012661A1

公开(公告)日：2023-01-19

申请号：US17936300

申请日：2022-09-28

Applicant: QUALCOMM Incorporated

Inventor： Hongtao Wang ,  Jianle Chen ,  Marta Karczewicz

IPC: H04N19/436 ,  H04N19/176 ,  G06N3/04 ,  H04N19/70 ,  H04N19/184 ,  H04N19/117

Abstract: A method of coding video data, the method comprising: reconstructing a block of the video data; and applying a Convolutional Neural Network (CNN)-based filter to the reconstructed block, wherein the CNN-based filter uses a LeakyReLU activation function.

公开(公告)号：US11496745B2

公开(公告)日：2022-11-08

申请号：US16909892

申请日：2020-06-23

Applicant: QUALCOMM Incorporated

Inventor： Marta Karczewicz ,  Yung-Hsuan Chao ,  Muhammed Zeyd Coban ,  Hongtao Wang

IPC: H04N19/14 ,  H04N19/70 ,  H04N19/176 ,  H04N19/46 ,  H04L65/70 ,  H04L65/75

Abstract: A video decoder can be configured to determine that a block of video data is encoded without transforming residual data for the block; determine a quantization parameter for the block of video data; based on the determined quantization parameter, determine a range for levels of quantized residual values of the block; divide the range into k intervals, wherein k is an integer value; determine a level for a quantized residual value of the block based on the k intervals by receiving information indicating the level for the quantized residual value is within a particular interval of the k intervals, receiving information indicating a difference value that represents a difference between a reference level value for the particular interval and the level for the quantized residual value of the block, and based on the reference level value and the difference value, determining the level for the quantized residual value.

公开(公告)号：US20220109860A1

公开(公告)日：2022-04-07

申请号：US17493543

申请日：2021-10-04

Applicant: QUALCOMM Incorporated

Inventor： Jianle Chen ,  Hongtao Wang ,  Venkata Meher Satchit Anand Kotra ,  Marta Karczewicz

IPC: H04N19/186 ,  H04N19/117 ,  H04N19/176 ,  G06N3/04 ,  G06N3/10

Abstract: An example device for decoding video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: apply a downsampling convolutional neural network layer to a first color component of a block of video data, the first color component of the block having a first size, wherein applying the downsampling convolutional neural network layer to the first color component generates a downsampled first color component having a second size smaller than the first size; filter a second color component having the second size to form a filtered second color component; concatenate the downsampled first color component with the filtered second color component to form concatenated color components; and filter the concatenated color components to form a filtered concatenated component including a filtered downsampled first color component.

公开(公告)号：US20220103864A1

公开(公告)日：2022-03-31

申请号：US17448658

申请日：2021-09-23

Applicant: QUALCOMM Incorporated

Inventor： Hongtao Wang ,  Venkata Meher Satchit Anand Kotra ,  Jianle Chen ,  Marta Karczewicz ,  Dana Kianfar ,  Auke Joris Wiggers

IPC: H04N19/70 ,  H04N19/44 ,  H04N19/172 ,  H04N19/192 ,  H04N19/80

Abstract: An example device for filtering decoded video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: decode a picture of video data; code a value for a syntax element representing a neural network model to be used to filter a portion of the decoded picture, the value representing an index into a set of pre-defined neural network models, the index corresponding to the neural network model in the set of pre-defined neural network models; and filter the portion of the decoded picture using the neural network model corresponding to the index.

公开(公告)号：US11228768B2

公开(公告)日：2022-01-18

申请号：US16991305

申请日：2020-08-12

Applicant: QUALCOMM Incorporated

Inventor： Marta Karczewicz ,  Yung-Hsuan Chao ,  Muhammed Zeyd Coban ,  Hongtao Wang

IPC: H04N19/157 ,  H04N19/176 ,  H04N19/132 ,  H04N19/124 ,  H04N19/463 ,  H04N19/122

Abstract: A method of decoding video data includes receiving a value indicating that a lossless mode is enabled for a block of the video data and, in response to determining that the value indicates that the lossless mode is enabled for the block of the video data, determining a maximum size for a lossless-coded transform block of the block of the video data is set to a maximum scanning size of the non-lossless coding block. The method further includes inverse scanning residual values for the block of the video data based on the maximum size for the lossless-coded transform block to generate a residual block for the block of the video data and reconstructing the block of the video data based on the residual block.