公开(公告)号：US11589037B2

公开(公告)日：2023-02-21

申请号：US17125486

申请日：2020-12-17

Applicant: QUALCOMM Incorporated

Inventor： Vadim Seregin ,  Yao-Jen Chang ,  Muhammed Zeyd Coban

IPC: H04N19/105 ,  H04N19/503 ,  H04N19/176

Abstract: A video coder is configured to determine a reference block of a reference picture for prediction of a current block of a current picture using motion information and to generate a set of reference samples for the current block of the current picture. To generate the set of reference samples, the video coder is configured to perform reference sample clipping on the reference block of the reference picture based on a size of the reference picture. The video coder is further configured to generate a prediction block for the current block of the current picture based on the set of reference samples.

公开(公告)号：US20220417563A1

公开(公告)日：2022-12-29

申请号：US17930533

申请日：2022-09-08

Applicant: QUALCOMM Incorporated

Inventor： Muhammed Zeyd Coban ,  Marta Karczewicz

IPC: H04N19/70 ,  H04N19/13 ,  H04N19/176 ,  H04N19/117 ,  H04N19/46

Abstract: As part of bypass decoding syntax elements for a set of coefficients in response to reaching a maximum number of regular coded bins, a video decoder is configured to receive a prefix value for a transform coefficient; decode the prefix value using Golomb-Rice coding; in response to a length of the prefix value being equal to a threshold value, receive a suffix value for the transform coefficient; decode the suffix value using exponential Golomb coding; and determine a level value for the transform coefficient based on the decoded prefix value and the decoded suffix value.

公开(公告)号：US11477486B2

公开(公告)日：2022-10-18

申请号：US16732008

申请日：2019-12-31

Applicant: QUALCOMM Incorporated

Inventor： Muhammed Zeyd Coban ,  Marta Karczewicz

IPC: H04N19/70 ,  H04N19/13 ,  H04N19/176 ,  H04N19/117 ,  H04N19/46

Abstract: As part of bypass decoding syntax elements for a set of coefficients in response to reaching a maximum number of regular coded bins, a video decoder is configured to receive a prefix value for a transform coefficient; decode the prefix value using Golomb-Rice coding; in response to a length of the prefix value being equal to a threshold value, receive a suffix value for the transform coefficient; decode the suffix value using exponential Golomb coding; and determine a level value for the transform coefficient based on the decoded prefix value and the decoded suffix value.

公开(公告)号：US11477464B2

公开(公告)日：2022-10-18

申请号：US17182686

申请日：2021-02-23

Applicant: QUALCOMM Incorporated

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

IPC: H04N19/186 ,  G06N3/04 ,  H04N19/90 ,  H04N19/172

Abstract: Systems and 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 a combined representation of the frame by combining 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. The process can include generating encoded video data based on the combined representation of the frame.

公开(公告)号：US11457242B2

公开(公告)日：2022-09-27

申请号：US16909447

申请日：2020-06-23

Applicant: QUALCOMM Incorporated

Inventor： Muhammed Zeyd Coban ,  Adarsh Krishnan Ramasubramonian ,  Vadim Seregin ,  Marta Karczewicz

IPC: H04N19/70

Abstract: A method of decoding video data includes decoding, from a coded video bitstream and as an unsigned integer 0-th order Exp-Golomb-coded syntax element with the left bit first, a value that specifies a target recovery point picture for a current picture of a current sequence of pictures, wherein the target recovery point picture is located at or after the current picture in display order; and recovering decoding of the current sequence of pictures at the target recovery point picture.

公开(公告)号：US11412264B2

公开(公告)日：2022-08-09

申请号：US17029550

申请日：2020-09-23

Applicant: QUALCOMM Incorporated

Inventor： Yao-Jen Chang ,  Muhammed Zeyd Coban ,  Marta Karczewicz

IPC: H04N19/70 ,  H04N19/96 ,  H04N19/119 ,  H04N19/136 ,  H04N19/172 ,  H04N19/174 ,  H04N19/176

Abstract: A video coder may code, in a picture parameter set (PPS), a syntax element indicative of a luma coding tree block size of coding tree units (CTUs) of a picture of video data to which the PPS is applicable. The video coder may further code the picture of the video data to which the PPS is applicable in accordance with the syntax element in the PPS.

公开(公告)号：US11245920B2

公开(公告)日：2022-02-08

申请号：US17000034

申请日：2020-08-21

Applicant: QUALCOMM Incorporated

Inventor： Muhammed Zeyd Coban ,  Hongtao Wang ,  Vadim Seregin ,  Marta Karczewicz

IPC: H04N11/02 ,  H04N19/52 ,  H04N19/176

Abstract: A device for coding video data is configured to code a motion vector difference (MVD) value using a codeword prefix and a codeword suffix. Based on an absolute value, minus 2, of the MVD value being 131070 or greater, the codeword prefix of the MVD value is equal to 1111 1111 1111 1111 and the codeword suffix is coded using the fixed length code.

公开(公告)号：US11202100B2

公开(公告)日：2021-12-14

申请号：US16814654

申请日：2020-03-10

Applicant: QUALCOMM Incorporated

Inventor： Marta Karczewicz ,  Muhammed Zeyd Coban ,  Hongtao Wang

IPC: H04N19/61 ,  H04N19/70 ,  H04N19/176

Abstract: A device for decoding video data performs coefficient coding for a residual block of video data encoded using a transform skip mode by determining values for a first neighboring coefficient and a second neighboring coefficient and determining a context offset for the coefficient currently being decoded based on the value for the first neighboring coefficient and the value for the second neighboring coefficient. Performing coefficient coding includes, for example, performing sign coding, level mapping, and context derivation. The device performs coefficient coding to determine the residual block and adds the residual block to a predicted block to determine a reconstructed block.

公开(公告)号：US20210368209A1

公开(公告)日：2021-11-25

申请号：US17325683

申请日：2021-05-20

Applicant: QUALCOMM Incorporated

Inventor： Muhammed Zeyd Coban ,  Vadim Seregin ,  Yong He ,  Yao-Jen Chang

IPC: H04N19/70 ,  H04N19/146 ,  H04N19/169 ,  H04N19/184

Abstract: A method of processing video data, the method comprising: decoding a syntax element in a profile tier level syntax structure in a bitstream that includes an encoded representation of the video data; and based on a value of the syntax element being equal to 0, inferring that all constraint fields in a general constraint information syntax structure have values indicating that constraints corresponding to the constraint fields do not apply to the bitstream.

公开(公告)号：US20210314623A1

公开(公告)日：2021-10-07

申请号：US17219147

申请日：2021-03-31

Applicant: QUALCOMM Incorporated

Inventor： Yao-Jen Chang ,  Vadim Seregin ,  Yong He ,  Muhammed Zeyd Coban ,  Marta Karczewicz

IPC: H04N19/70 ,  H04N19/159 ,  H04N19/136

Abstract: A method of processing video data comprises performing a bitstream conformance process that determines whether a bitstream that comprises an encoded representation of the video data conforms to a video coding standard, wherein the bitstream conformance process determines that the bitstream does not conform to the video coding standard when at least one of: a chroma-related constraint flag is equal to 0 and when there are no chroma components for pictures in the bitstream, or an inter prediction-related constraint flag is equal to 0 when all slices of the bitstream are I slices.