公开(公告)号：US11350109B2

公开(公告)日：2022-05-31

申请号：US16999741

申请日：2020-08-21

Applicant: QUALCOMM Incorporated

Inventor： Kai Zhang ,  Jianle Chen ,  Li Zhang ,  Xiang Li ,  Marta Karczewicz

IPC: H04N19/159 ,  H04N19/513 ,  H04N19/182 ,  H04N19/107 ,  H04N19/463 ,  H04N19/503 ,  H04N19/11 ,  H04N19/124 ,  H04N19/139 ,  H04N19/176 ,  H04N19/44 ,  H04N19/593 ,  H04N19/186

Abstract: Techniques are described for using an inter-intra-prediction block. A video coder may generate a first prediction block according to an intra-prediction mode and generate a second prediction block according to an inter-prediction mode. The video coder may weighted combine, such as based on the intra-prediction mode, the two prediction blocks to generate an inter-intra-prediction block (e.g., final prediction block). In some examples, an inter-intra candidate is identified in a list of candidate motion vector predictors, and an inter-intra-prediction block is used based on identification of the inter-intra candidate in the list of candidate motion vector predictors.

公开(公告)号：US20220103845A1

公开(公告)日：2022-03-31

申请号：US17489459

申请日：2021-09-29

Applicant: QUALCOMM Incorporated

Inventor： Hongtao Wang ,  Jianle Chen ,  Marta Karczewicz

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

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：US20210195195A1

公开(公告)日：2021-06-24

申请号：US17197883

申请日：2021-03-10

Applicant: QUALCOMM Incorporated

Inventor： Xin Zhao ,  Vadim Seregin ,  Marta Karczewicz ,  Jianle Chen

IPC: H04N19/124 ,  H04N19/61 ,  H04N19/176 ,  H04N19/12 ,  H04N19/103

Abstract: Example techniques are described to illustrate multiple transform applied for Intra prediction residual. It may be used in the context of advanced video codecs, such as extensions of HEVC or the next generation of video coding standards. A video encoder and a video decoder may select transform subsets that each identify one or more candidate transforms. The video encoder and the video decoder may determine transforms from the selected transform subsets.

公开(公告)号：US10785494B2

公开(公告)日：2020-09-22

申请号：US16131860

申请日：2018-09-14

Applicant: QUALCOMM Incorporated

Inventor： Wei-Jung Chien ,  Hsiao-Chiang Chuang ,  Xiang Li ,  Jianle Chen ,  Li Zhang ,  Marta Karczewicz

IPC: H04N19/44 ,  H04N19/513 ,  H04N19/577 ,  H04N19/176 ,  H04N19/523 ,  H04N19/56 ,  H04N19/52 ,  H04N19/573

Abstract: A method of decoding video data includes constructing, by a video decoder implemented in processing circuitry, a candidate list of motion vector information for a portion of a current frame. The method includes receiving, by the video decoder, signaling information indicating starting motion vector information of the candidate list of motion vector information, the starting motion vector information indicating an initial position in a reference frame. The method includes refining, by the video decoder, based on one or more of bilateral matching or template matching, the starting motion vector information to determine refined motion vector information indicating a refined position in the reference frame that is within a search range from the initial position. The method includes generating, by the video decoder, a predictive block based on the refined motion vector information and decoding, by the video decoder, the current frame based on the predictive block.

公开(公告)号：US10764587B2

公开(公告)日：2020-09-01

申请号：US16020179

申请日：2018-06-27

Applicant: QUALCOMM Incorporated

Inventor： Kai Zhang ,  Jianle Chen ,  Xin Zhao ,  Marta Karczewicz

IPC: H04N19/159 ,  H04N19/593 ,  H04N19/109 ,  H04N19/11 ,  H04N19/176 ,  H04N19/186 ,  H04N19/70

Abstract: An apparatus configured to encode or decode video data that includes a memory configured to store at least one reconstructed sample of video data and at least one processor, in communication with the memory, that is configured to identify at least one reconstructed sample, determine at least one extended angular intra prediction mode to use for intra prediction of at least one sample of a current block, intra predict, using the at least one extended angular intra prediction mode, at least one sample of the current block based on the at least one reconstructed sample, extended angular intra prediction modes including angular intra prediction modes other than angular prediction modes between horizontal −45 degrees and vertical −45 degrees, and encode or decode the current block based on the at least one predicted sample.

公开(公告)号：US10701366B2

公开(公告)日：2020-06-30

申请号：US15900649

申请日：2018-02-20

Applicant: QUALCOMM Incorporated

Inventor： Yi-Wen Chen ,  Wei-Jung Chien ,  Hsiao-Chiang Chuang ,  Jianle Chen ,  Xiang Li ,  Marta Karczewicz ,  Yu-Chen Sun

IPC: H04N7/12 ,  H04N19/139 ,  H04N19/182 ,  H04N19/176 ,  H04N19/124 ,  H04N19/513 ,  H04N19/577 ,  H04N19/117 ,  H04N19/105 ,  H04N19/573 ,  H04N19/44 ,  H04N19/109 ,  H04N19/51 ,  H04N19/583

Abstract: An example device for decoding video data includes a memory configured to store video data, and a video decoder implemented in circuitry and configured to determine that motion information of a current block of the video data is to be derived using decoder-side motion vector derivation (DMVD), determine a pixels clue for the current block, the pixels clue comprising pixel data obtained from one or more groups of previously decoded pixels, derive the motion information for the current block according to DMVD from the pixels clue, and decode the current block using the motion information. The video decoder may generate the pixels clue using multiple hypothesis predictions from multiple motion compensated blocks. The video decoder may determine an inter-prediction direction for the motion information according to matching costs between different prediction directions. The video decoder may refine the motion information using a calculated matching cost for the pixels clue.

公开(公告)号：US10694181B2

公开(公告)日：2020-06-23

申请号：US15879359

申请日：2018-01-24

Applicant: QUALCOMM Incorporated

Inventor： Li Zhang ,  Jianle Chen ,  Wei-Jung Chien ,  Marta Karczewicz

IPC: H04N19/117 ,  H04N19/176 ,  H04N19/82 ,  H04N19/159 ,  H04N19/186 ,  H04N19/14 ,  H04N19/86 ,  H04N19/182 ,  H04N19/436

Abstract: An example method of filtering a reconstructed block of video data includes obtaining, by one or more processors, reconstructed samples of a current block of the video data; and selectively bilaterally filtering, by the one or more processors, the reconstructed samples of the current block to generate a filtered current block. In this example, selectively bilaterally filtering the reconstructed samples of the current block comprises refraining from bilaterally filtering at least one reconstructed sample of the current block such that the filtered current block includes at least one non-bilaterally filtered sample.

公开(公告)号：US10687077B2

公开(公告)日：2020-06-16

申请号：US16011340

申请日：2018-06-18

Applicant: QUALCOMM Incorporated

Inventor： Kai Zhang ,  Xiang Li ,  Jianle Chen ,  Li Zhang ,  Marta Karczewicz

IPC: H04N19/56 ,  H04N19/176 ,  H04N19/52 ,  H04N19/196 ,  H04N19/159 ,  H04N19/109 ,  H04N19/172

Abstract: Techniques are directed to a device for decoding a current block of video data in a current coding picture. The device may include a memory configured to store video data. The device may also include a processor configured to generate a first prediction block for the current block of the video data in the current picture according to an intra-prediction mode and generate a second prediction block for the current block of the video data in the current picture the picture according to an inter-prediction mode. The processor may be configured to generate motion information propagated from the second prediction block of the picture to the first prediction block, and use the motion information to obtain a final prediction block, then generate a reconstructed block based on a combination of the final prediction block and a residual block.

公开(公告)号：US10560712B2

公开(公告)日：2020-02-11

申请号：US15587044

申请日：2017-05-04

Applicant: QUALCOMM Incorporated

Inventor： Feng Zou ,  Jianle Chen ,  Marta Karczewicz ,  Xiang Li ,  Hsiao-Chiang Chuang ,  Wei-Jung Chien

IPC: H04N19/513 ,  H04N19/124 ,  H04N19/18 ,  H04N19/44 ,  H04N19/567 ,  H04N19/91

Abstract: An example method includes obtaining, for a current block of video data, values of motion vectors (MVs) of an affine motion model of a neighboring block of video data; deriving, from the values of the MVs of the affine motion model of the neighboring block, values of predictors for MVs of an affine motion model of the current block; decoding, from a video bitstream, a representation of differences between the values of the MVs of the affine motion model for the current block and the values of the predictors; determining the values of the MVs of the affine motion model for the current block from the values of the predictors and the decoded differences; determining, based on the determined values of the MVs of the affine motion model for the current block, a predictor block of video data; and reconstructing the current block based on the predictor block.

公开(公告)号：US10531116B2

公开(公告)日：2020-01-07

申请号：US14592767

申请日：2015-01-08

Applicant: QUALCOMM Incorporated

Inventor： Xiang Li ,  Joel Sole Rojals ,  Marta Karczewicz ,  Hongbin Liu ,  Li Zhang ,  Jianle Chen

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

Abstract: A device for decoding video data includes a memory configured to store video data and a video decoder comprising one or more processors configured to adaptively select motion vector precision for motion vectors used to encode blocks of video data.