公开(公告)号：US12238328B2

公开(公告)日：2025-02-25

申请号：US18514809

申请日：2023-11-20

Applicant: Panasonic Intellectual Property Corporation of America

Inventor： Jing Ya Li ,  Chong Soon Lim ,  Ru Ling Liao ,  Hai Wei Sun ,  Han Boon Teo ,  Kiyofumi Abe ,  Tadamasa Toma ,  Takahiro Nishi

IPC: H04N19/52 ,  H04N19/12 ,  H04N19/174 ,  H04N19/182

Abstract: An encoder includes circuitry and memory connected to the circuitry. In operation, the circuitry: corrects a base motion vector using a correction value for correcting the base motion vector in a predetermined direction; and encodes a current partition to be encoded in an image of a video, using the base motion vector corrected. The correction value is specified by a first parameter and a second parameter, the first parameter indicating a table to be selected from among a plurality of tables each including values, the second parameter indicating one of the values included in the table to be selected indicated by the first parameter. In each of the plurality of tables, a smaller value among the values is assigned a smaller index. Each of the plurality of tables includes a different minimum value among the values.

公开(公告)号：US12231639B2

公开(公告)日：2025-02-18

申请号：US18516398

申请日：2023-11-21

Applicant: Dolby Laboratories Licensing Corporation

Inventor： Jong Ki Han ,  Chan Won Seo ,  Kwang Hyun Choi

IPC: H04N19/124 ,  H04L45/745 ,  H04N19/11 ,  H04N19/117 ,  H04N19/12 ,  H04N19/136 ,  H04N19/14 ,  H04N19/159 ,  H04N19/176 ,  H04N19/61 ,  H04N19/109 ,  H04N19/132 ,  H04N19/17 ,  H04N19/597 ,  H04N19/82

Abstract: According to the present invention, an adaptive scheme is applied to an image encoding apparatus that includes an inter-predictor, an intra-predictor, a transformer, a quantizer, an inverse quantizer, and an inverse transformer, wherein input images are classified into two or more different categories, and two or more modules from among the inter-predictor, the intra-predictor, the transformer, the quantizer, and the inverse quantizer are implemented to perform respective operations in different schemes according to the category to which an input image belongs. Thus, the invention has the advantage of efficiently encoding an image without the loss of important information as compared to a conventional image encoding apparatus which adopts a packaged scheme.

公开(公告)号：US12219136B2

公开(公告)日：2025-02-04

申请号：US18339046

申请日：2023-06-21

Applicant: Beijing Bytedance Network Technology Co., Ltd. ,  Bytedance Inc.

Inventor： Li Zhang ,  Kai Zhang ,  Jizheng Xu ,  Hongbin Liu ,  Yue Wang

IPC: H04N19/12 ,  H04N19/176 ,  H04N19/18 ,  H04N19/48 ,  H04N19/60

Abstract: A video processing method includes determining, for a conversion between a current block of a video and a bitstream representation of the video, whether to enable a level mapping operation or a level remapping operation based on a rule, wherein the level mapping operation or the level remapping operation includes changing between a first representation of a residual coefficient of the current block and a second representation of the residual coefficient of the current block based on neighboring residual coefficients of the residual coefficient; and performing the conversion by selectively using the level mapping operation or the level remapping operation based on the determining.

公开(公告)号：US20250016385A1

公开(公告)日：2025-01-09

申请号：US18894444

申请日：2024-09-24

Applicant: Beijing Bytedance Network Technology Co., Ltd. ,  Bytedance Inc.

Inventor： Kai Zhang ,  Li Zhang ,  Hongbin Liu ,  Jizheng Xu ,  Yue Wang

IPC: H04N19/96 ,  H04N19/119 ,  H04N19/12 ,  H04N19/122 ,  H04N19/13 ,  H04N19/132 ,  H04N19/136 ,  H04N19/157 ,  H04N19/172 ,  H04N19/176 ,  H04N19/184 ,  H04N19/186 ,  H04N19/46 ,  H04N19/70

Abstract: A method for processing a video includes determining, for a conversion between a current video block and a bitstream representation of the current video block, whether to apply unsymmetrical quad-trees (UQTs) splitting, and a specific UQT type to be used for splitting the current video block if UQT splitting is applied, based on a slice or a picture containing the current video block; and performing the conversion based on the determining.

公开(公告)号：US12192525B2

公开(公告)日：2025-01-07

申请号：US18352796

申请日：2023-07-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaehong Jung ,  Juhyung Son ,  Dongcheol Kim ,  Geonjung Ko ,  Jinsam Kwak

IPC: H04N19/176 ,  H04N19/12 ,  H04N19/61 ,  H04N19/625

Abstract: A video signal processor is configured to: obtain at least one transform block for a residual signal of a current block from a video signal bitstream, wherein the transform block comprises a plurality of transform coefficients two-dimensionally arranged, determine, on the basis of length information of a first side of the transform block, a horizontal transform kernel for horizontal transformation of the transform block, regardless of a length of a second side of the transform block, which is orthogonal to the first side, determine, on the basis of length information of the second side, a vertical transform kernel for vertical transformation of the transform block, regardless of a length of the first side, obtain the residual signal of the current block by performing, on the transform block, inverse transformation using the horizontal transform kernel and the vertical transform kernel, and reconstruct the current block based on the residual signal.

公开(公告)号：US12192462B2

公开(公告)日：2025-01-07

申请号：US17775583

申请日：2020-12-11

Applicant: Sony Group Corporation

Inventor： Takeshi Tsukuba

IPC: H04N19/00 ,  H04N19/12 ,  H04N19/124 ,  H04N19/156 ,  H04N19/157 ,  H04N19/186 ,  H04N19/46 ,  H04N19/61 ,  H04N19/625

Abstract: The present disclosure relates to an image processing device and method for enabling suppression of an increase in encoding load.
An encoding mode of encoding of an image is set by setting a transform type with a minimum encoding cost in a non-joint chrominance encoding mode as a transform type in a joint chrominance encoding mode, and deriving an encoding cost in the joint chrominance encoding mode. The present disclosure can be applied to, for example, an image processing device, an image encoding device, an information processing device, an electronic device, an image processing method, an information processing method, or the like.

公开(公告)号：US20250008158A1

公开(公告)日：2025-01-02

申请号：US18753532

申请日：2024-06-25

Applicant: GOOGLE LLC

Inventor： Jin Zhao ,  In Suk Chong

IPC: H04N19/625 ,  H04N19/12 ,  H04N19/176

Abstract: A size of a transform block is identified. A transform type for the transform block is identified. The transform type includes a horizontal transform type and a vertical transform type. Identifying the transform type includes determining whether the size of the transform block is below a predefined block size; and, in response to determining that the size is below the predefined block size, selecting a default transform type for each of the horizontal transform type and the vertical transform type. The transform type is then applied to the transform block. The default transform type can be the discrete cosine transform (DCT).

公开(公告)号：US20240430463A1

公开(公告)日：2024-12-26

申请号：US18338731

申请日：2023-06-21

Applicant: City University of Hong Kong

Inventor： Sam Tak Wu Kwong ,  Haifeng Guo ,  Shiqi Wang ,  Dongjie Ye

IPC: H04N19/42 ,  H04N19/12 ,  H04N19/139 ,  H04N19/172 ,  H04N19/176 ,  H04N19/60 ,  H04N19/85

Abstract: There is provided a computer-implemented method for learned video compression, which includes processing a current frame (xt) and previously decoded frame ({circumflex over (x)}t−1) of a video data using a motion estimation model to estimate a motion vector (vt) for every pixel, compressing the motion vector (vt) and reconstructing the motion vector (vt) to a reconstructed motion vector ({circumflex over (v)}t), applying an enhanced context mining (ECM) model to obtain enhanced context ({umlaut over (C)}E) from the reconstructed motion vector ({circumflex over (v)}t) and previously decoded frame feature (x̆t−1), compressing the current frame (xt) with the assistance of the enhanced context ({umlaut over (C)}E) to obtain a reconstructed frame ({circumflex over (x)}t′), and providing the reconstructed frame ({circumflex over (x)}t′) to a post-enhancement backend network to obtain a high-resolution frame ({circumflex over (x)}t).

公开(公告)号：US20240422316A1

公开(公告)日：2024-12-19

申请号：US18818526

申请日：2024-08-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Kai Cui ,  Atanas Boev ,  Eckehard Steinbach ,  Elena Alexandrovna Alshina ,  Ahmet Burakhan Koyuncu

IPC: H04N19/12 ,  H04N19/119 ,  H04N19/17 ,  H04N19/33 ,  H04N19/42 ,  H04N19/625 ,  H04N19/63

Abstract: The present disclosure relates to image modification such as an image enhancement wherein the processing is at least partially based on neural networks. In particular, the image modification includes a multi-channel processing in which a primary channel is processed separately and secondary channels are processed based on the processed primary channel. The primary channel is processed based on a first spatial frequency transform to obtain a transformed primary channel and the secondary channel is processed based on a second spatial frequency transform to obtain a transformed secondary channel. The transformed primary channel is processed by means of a first neural network to obtain a modified transformed primary channel and the transformed secondary channel is processed based on the transformed primary channel by means of a second neural network to obtain a modified transformed secondary channel.

公开(公告)号：US12170757B2

公开(公告)日：2024-12-17

申请号：US17451972

申请日：2021-10-22

Applicant: NVIDIA Corporation

Inventor： Ranga Ramanujam Srinivasan ,  Jianjun Chen ,  Dong Zhang ,  Wei Feng ,  Xi He

IPC: H04N7/12 ,  H04N19/105 ,  H04N19/119 ,  H04N19/12 ,  H04N19/132 ,  H04N19/159 ,  H04N19/176 ,  H04N19/61

Abstract: Disclosed are apparatuses, systems, and techniques for real-time codec encoding of video files using hardware-assisted accelerators that utilize a combination of parallel and sequential processing, in which at least a part of intra-frame block prediction is performed with parallel processing.