公开(公告)号：US20240308505A1

公开(公告)日：2024-09-19

申请号：US18183867

申请日：2023-03-14

Applicant: QUALCOMM Incorporated

Inventor： Thomas Alexander RYDER ,  Muhammed Zeyd COBAN ,  Marta KARCZEWICZ

IPC: B60W30/095 ,  G06T7/215

CPC classification number: B60W30/0953 ,  G06T7/215

Abstract: A device includes one or more processors configured to obtain encoded data associated with one or more motion values. The one or more processors are also configured to obtain conditional input of a compression network, wherein the conditional input is based on one or more first predicted motion values. The one or more processors are further configured to process, using the compression network, the encoded data and the conditional input to generate one or more second predicted motion values.

公开(公告)号：US20230101318A1

公开(公告)日：2023-03-30

申请号：US17930331

申请日：2022-09-07

Applicant: QUALCOMM Incorporated

Inventor： Venkata Meher Satchit Anand KOTRA ,  Nan HU ,  Vadim SEREGIN ,  Marta KARCZEWICZ

IPC: H04N19/117 ,  H04N19/186

Abstract: Systems and techniques are described for processing video data. For instance, a process can include obtaining video data. The process can further include determining a classification band for a first sample of the video data using at least chroma information from the first sample, collocated luma information and collocated chroma information. The process can also include filtering at least the first sample of the video data based on the classification band.

公开(公告)号：US20220279177A1

公开(公告)日：2022-09-01

申请号：US17686817

申请日：2022-03-04

Applicant: QUALCOMM Incorporated

Inventor： Nan HU ,  Vadim SEREGIN ,  Marta KARCZEWICZ

IPC: H04N19/117 ,  H04N19/176 ,  H04N19/46 ,  H04N19/96 ,  H04N19/136 ,  H04N19/182 ,  H04N19/86 ,  H04N19/174

Abstract: Systems, methods, and media are provided for loop filtering across raster scan slices. One example includes obtaining the video data comprising one or more pictures and a first block of a picture having a pixel subject to filtering. A second block is determined to be located in the first slice in a particular relation to the second block. A third block that includes pixels for filtering the pixel is determined to be in a second slice at a diagonal corner of the first block, with filtering across slice boundaries disabled. First one or more pixels of the second block are identified as available for performing loop filtering of the pixel and second one or more pixels of the third block identified as unavailable for performing the loop filtering of the pixel of the first block. The first one or more pixels and the second one or more pixels are padded.

公开(公告)号：US20220201282A1

公开(公告)日：2022-06-23

申请号：US17534325

申请日：2021-11-23

Applicant: QUALCOMM Incorporated

Inventor： Yao-Jen CHANG ,  Jingya LI ,  Vadim SEREGIN ,  Marta KARCZEWICZ

IPC: H04N19/105 ,  H04N19/513 ,  H04N19/573 ,  H04N19/139 ,  H04N19/176

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.

公开(公告)号：US20220191523A1

公开(公告)日：2022-06-16

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 ,  H04N19/172 ,  H04N19/124 ,  H04N19/186 ,  H04N19/91

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：US20220086463A1

公开(公告)日：2022-03-17

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 ,  H04N19/172 ,  H04N19/90 ,  G06N3/04

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：US20210274189A1

公开(公告)日：2021-09-02

申请号：US17321302

申请日：2021-05-14

Applicant: Qualcomm Incorporated

Inventor： Vadim SEREGIN ,  Wei-Jung CHIEN ,  Han HUANG ,  Marta KARCZEWICZ

IPC: H04N19/14 ,  H04N19/105 ,  H04N19/176 ,  H04N19/423 ,  H04N19/119

Abstract: A video coder can be configured to code video data by determining a first block size threshold for a block of video data; determining a second block size threshold, wherein the second block size threshold is smaller than the first block size threshold; partitioning the block of video data into smaller sub-blocks; in response to determining that a first partition of the partitioned block is smaller or equal to the first block size threshold, determining that blocks within the partition belong to a parallel estimation area; and in response to determining that a second partition of the partitioned block is smaller or equal to the second block size threshold, determining that blocks within the second partition belong to an area for a shared candidate list.

公开(公告)号：US20210099724A1

公开(公告)日：2021-04-01

申请号：US16982013

申请日：2019-09-26

Applicant: Qualcomm Incorporated

Inventor： Yu HAN ,  Kai ZHANG ,  Li ZHANG ,  Wei-Jung CHIEN ,  Marta KARCZEWICZ

IPC: H04N19/44 ,  H04N19/137 ,  H04N19/105 ,  H04N19/159 ,  H04N19/176

Abstract: Methods and devices for decoding including a processor configured to determine which picture is a collocated picture, and determine a location of an associated block of the video data in the collocated picture that corresponds to the current block of video data in the current coding picture, based on using previously decoded blocks in the current coding picture to find an initial motion vector between the associated block in the collocated picture and the current block in the current coding picture, where the associated block of the video data includes at least one first derived motion vector. The processor configured to determine at least one second derived motion vector associated with the current block in the current coding picture, when the initial motion vector points to the collocated picture, based on the at least on first derived motion vector associated with the associated block in the collocated picture.

公开(公告)号：US20210092458A1

公开(公告)日：2021-03-25

申请号：US17024614

申请日：2020-09-17

Applicant: QUALCOMM Incorporated

Inventor： Vadim SEREGIN ,  Muhammed Zeyd COBAN ,  Marta KARCZEWICZ

IPC: H04N19/82 ,  H04N19/187 ,  H04N19/58

Abstract: Systems, methods, and computer-readable storage media for signaling filters for reference picture resampling are described. One example involves obtaining an encoded video bitstream associated with the video data, identifying a current picture and at least one reference picture from the encoded video bitstream, and identifying signaling data from the encoded video bitstream for the video data, the signaling data including a partial set of coefficient data for at least one filter. A complete set of coefficients (e.g., filter coefficients) is derived for the at least one filter from the partial set of coefficient data and characteristics of the at least one filter, and the current picture is processed using the complete set of coefficients for the at least one filter.

公开(公告)号：US20210014537A1

公开(公告)日：2021-01-14

申请号：US16921106

申请日：2020-07-06

Applicant: QUALCOMM Incorporated

Inventor： Nan HU ,  Vadim SEREGIN ,  Adarsh Krishnan RAMASUBRAMONIAN ,  Muhammed Zeyd COBAN ,  Marta KARCZEWICZ

IPC: H04N19/80 ,  H04N19/176 ,  H04N19/174 ,  H04N19/119 ,  H04N19/172

Abstract: Systems, methods, and media are provided for loop filtering across raster scan slices. One example includes obtaining data comprising one or more pictures, including obtaining a first block located in a first slice of one of the pictures. The example then includes determining a second block is located in a second slice of the picture, the second block including one or more pixels for use in performing loop filtering of a pixel of the first block, and determining that loop filtering across slice boundaries is disabled. Based on this disabling, the example determines that the one or more pixels of the second block are unavailable for performing loop filtering of the pixel of the first block, and duplicates at least one pixel of the first block or at least one pixel of an additional block of the first slice for performing loop filtering of the pixel of the first block.