公开(公告)号：US12225205B2

公开(公告)日：2025-02-11

申请号：US17825575

申请日：2022-05-26

Applicant: TENCENT AMERICA LLC

Inventor： Sheng Lin ,  Wei Jiang ,  Shan Liu ,  Wei Wang

IPC: H04N19/149 ,  H04N19/176 ,  H04N19/60 ,  H04N19/91

Abstract: Systems and methods for block-wise entropy coding methods in neural image compression is provided. A method includes: receiving a bitstream that includes an image; partitioning the image into a plurality of blocks; compressing each of the plurality of blocks by a neural network-based encoder; obtaining compressed features by obtaining a compressed feature for each block from among the plurality of blocks in the image; processing the compressed features by an entropy encoder to generate a first compressed bitstream; obtaining a plurality of reshaped compressed features by concatenating the compressed features; processing the plurality of reshaped compressed features by the entropy encoder to generate a second compressed bitstream; and encoding the bitstream including the image based on the second compressed bitstream.

公开(公告)号：US20250024042A1

公开(公告)日：2025-01-16

申请号：US18621713

申请日：2024-03-29

Applicant: Tencent America LLC

Inventor： Ding DING ,  Xin ZHAO ,  Shan LIU

IPC: H04N19/149 ,  H04N19/105 ,  H04N19/154

Abstract: Methods, apparatus, and computer readable storage medium evaluating codec performance. One method includes obtaining m anchor data points each generated based on a respective anchor encoded video bitstream; obtaining n test data points each generated based on a respective encoded test video bitstream, n being an integer; fitting the m anchor data points with an anchor curve, the anchor curve being based on an anchor polynomial, wherein the anchor polynomial is monotonic in an x-axis range; fitting the n test data points with a test curve, the anchor curve being based on a test polynomial, wherein the test polynomial is monotonic in the x-axis range; and evaluating the test codec performance based on the anchor curve and the test curve, to obtain an evaluation result.

公开(公告)号：US12200222B2

公开(公告)日：2025-01-14

申请号：US18521810

申请日：2023-11-28

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： Jiancong Luo ,  Yuwen He ,  Wei Chen

IPC: H04N19/137 ,  H04N19/105 ,  H04N19/149 ,  H04N19/176

Abstract: Systems and methods are described for video coding using affine motion prediction. In an example method, motion vector gradients are determined from respective motion vectors of a plurality of neighboring sub-blocks neighboring a current block. An estimate of at least one affine parameter for the current block is determined based on the motion vector gradients. An affine motion model is determined based at least in part on the estimated affine parameter(s), and a prediction of the current block is generated using the affine motion model. The estimated parameter(s) may be used in the affine motion model itself. Alternatively, the estimated parameter(s) may be used in a prediction of the affine motion model. In some embodiments, only neighboring sub-blocks above and/or to the left of the current block are used in estimating the affine parameter(s).

公开(公告)号：US20250016349A1

公开(公告)日：2025-01-09

申请号：US18777052

申请日：2024-07-18

Applicant: Huawei Technologies Co., Ltd.

Inventor： Ye-Kui Wang

IPC: H04N19/44 ,  H04N19/149 ,  H04N19/154 ,  H04N19/169 ,  H04N19/172 ,  H04N19/187 ,  H04N19/30 ,  H04N19/423 ,  H04N19/46 ,  H04N19/70

Abstract: A video coding mechanism is disclosed. The mechanism includes encoding a bitstream comprising a video parameter set (VPS) and one or more sublayers. A buffering period (BP) supplemental enhancement information (SEI) message comprising a BP maximum sublayers minus one (bp_max_sublayers_minus1) is also encoded into the bitstream. The bp_max_sublayers_minus1 is set to a value in a range of zero to a maximum number of sublayers indicated in the VPS. A hypothetical reference decoder (HRD) is initialized based on the BP SEI message. A set of bitstream conformance tests are performed on the sublayers. The bitstream is stored for communication toward a decoder.

公开(公告)号：US12170780B2

公开(公告)日：2024-12-17

申请号：US18369315

申请日：2023-09-18

Applicant: TEXAS INSTRUMENTS INCORPORATED

Inventor： Hrushikesh Tukaram Garud ,  Mihir Narendra Mody ,  Soyeb Nagori

IPC: H04N19/86 ,  H04N19/117 ,  H04N19/147 ,  H04N19/149 ,  H04N19/176 ,  H04N19/182 ,  H04N19/82

Abstract: The disclosure provides a sample adaptive offset (SAO) encoder. The SAO encoder includes a statistics collection (SC) block and a rate distortion optimization (RDO) block coupled to the SC block. The SC block receives a set of deblocked pixels and a set of original pixels. The SC block categorizes each deblocked pixel of the set of deblocked pixels in at least one of a plurality of band and edge categories. The SC block estimates an error in each category as difference between a deblocked pixel of the set of deblocked pixels and corresponding original pixel of the set of original pixels. The RDO block determines a set of candidate offsets associated with each category and selects a candidate offset with a minimum RD cost. The minimum RD cost is used by a SAO type block and a decision block to generate final offsets for the SAO encoder.

公开(公告)号：US20240380888A1

公开(公告)日：2024-11-14

申请号：US18784695

申请日：2024-07-25

Applicant: Sony Group Corporation

Inventor： Atsushi YAMATO ,  Takeshi TSUKUBA

IPC: H04N19/13 ,  H04N19/149 ,  H04N19/176 ,  H04N19/70

Abstract: An upper limit value of the number of bins allocated to a processing target subblock by distributing the number of bins among nonzero subblocks is set, a syntax element value regarding the processing target subblock is derived by using coefficient data derived from image data so that the number of bins does not exceed the upper limit value, and the syntax element value derived is encoded and coded data is generated. The present disclosure can be applied, for example, to an image processing apparatus, an image encode apparatus, an image decode apparatus, a transmitting apparatus, a receiving apparatus, a transmitting/receiving apparatus, an information processing apparatus, an imaging apparatus, a reproducing apparatus, an electronic device, an image processing method, an information processing method, and the like.

公开(公告)号：US12120352B2

公开(公告)日：2024-10-15

申请号：US17208100

申请日：2021-03-22

Applicant: LG ELECTRONICS INC.

Inventor： Jung Sun Kim ,  Seung Wook Park ,  Young Hee Choi ,  Jaewon Sung ,  Byeong Moon Jeon ,  Joon Young Park

IPC: H04N19/625 ,  H04N19/119 ,  H04N19/122 ,  H04N19/129 ,  H04N19/149 ,  H04N19/176 ,  H04N19/18 ,  H04N19/61

CPC classification number: H04N19/61 ,  H04N19/119 ,  H04N19/122 ,  H04N19/129 ,  H04N19/149 ,  H04N19/176 ,  H04N19/18 ,  H04N19/625

Abstract: The present invention relates to a method for decoding a video signal, comprising the steps of: acquiring a transform size flag of the current macroblock from a video signal; checking the number of non-zero transform coefficients at each pixel position in a first transform block which corresponds to the transform size flag; changing a scan order of the first transform block by prioritizing the position of the pixel having the greatest number of the non-zero transform coefficients in the first transform block; determining the number of the non-zero transform coefficients at each pixel position in a second transform block, and setting the changed scan order of the first transform block as an initialized scan order of the second transform block; adding the number of the non-zero transform coefficients at each pixel position in the first transform block and the number of the non-zero transform coefficients at each pixel position in the second transform block, and changing the scan order of the second transform block by prioritizing the position of the pixel having the greatest number of the non-zero transform coefficients; and decoding the transform coefficients arranged in the scan order changed in the previous step, wherein the first transform block and the second transform block have sizes corresponding to the transform size flag, and are contained in the current macroblock.

公开(公告)号：US20240305783A1

公开(公告)日：2024-09-12

申请号：US18667917

申请日：2024-05-17

Applicant: DOLBY LABORATORIES LICENSING CORPORATION

Inventor： Athanasios Leontaris ,  Alexandros Tourapis

IPC: H04N19/124 ,  H04N19/126 ,  H04N19/137 ,  H04N19/14 ,  H04N19/142 ,  H04N19/149 ,  H04N19/15 ,  H04N19/152 ,  H04N19/154 ,  H04N19/159 ,  H04N19/172 ,  H04N19/174 ,  H04N19/176 ,  H04N19/194 ,  H04N19/61 ,  H04N19/615 ,  H04N19/80

CPC classification number: H04N19/124 ,  H04N19/137 ,  H04N19/14 ,  H04N19/142 ,  H04N19/15 ,  H04N19/154 ,  H04N19/159 ,  H04N19/194 ,  H04N19/615 ,  H04N19/80 ,  H04N19/126 ,  H04N19/149 ,  H04N19/152 ,  H04N19/172 ,  H04N19/174 ,  H04N19/176 ,  H04N19/61

Abstract: Embodiments feature families of rate allocation and rate control methods that utilize advanced processing of past and future frame/field picture statistics and are designed to operate with one or more coding passes. At least two method families include: a family of methods for a rate allocation with picture look-ahead; and a family of methods for average bit rate (ABR) control methods. At least two other methods for each method family are described. For the first family of methods, some methods may involve intra rate control. For the second family of methods, some methods may involve high complexity ABR control and/or low complexity ABR control. These and other embodiments can involve any of the following: spatial coding parameter adaptation, coding prediction, complexity processing, complexity estimation, complexity filtering, bit rate considerations, quality considerations, coding parameter allocation, and/or hierarchical prediction structures, among others.

公开(公告)号：US12088811B2

公开(公告)日：2024-09-10

申请号：US17093671

申请日：2020-11-10

Applicant: Texas Instruments Incorporated

Inventor： Naveen Srinivasamurthy ,  Soyeb Nagori ,  Manoj Koul

IPC: H04N19/132 ,  H04N19/126 ,  H04N19/152 ,  H04N19/157 ,  H04N19/172 ,  H04N19/124 ,  H04N19/149

CPC classification number: H04N19/132 ,  H04N19/126 ,  H04N19/152 ,  H04N19/157 ,  H04N19/172 ,  H04N19/124 ,  H04N19/149

Abstract: Several methods and systems for encoding pictures associated with video data are disclosed. In an embodiment, a method includes determining by a processing module, whether a picture is to be encoded based on at least one of a skip assessment associated with the picture and an encoding status of a pre-selected number of pictures preceding the picture in an encoding sequence. The method further includes encoding by the processing module, a plurality of rows of video data associated with the picture upon determining that the picture is to be encoded, wherein the plurality of rows are encoded based on a pre-selected maximum encoded picture size.

公开(公告)号：US20240244227A1

公开(公告)日：2024-07-18

申请号：US18096424

申请日：2023-01-12

Applicant: Mellanox Technologies, Ltd.

Inventor： Eshed Ram ,  Dotan David Levi ,  Assaf Hallak ,  Shie Mannor ,  Gal Chechik ,  Eyal Frishman ,  Ohad Markus ,  Dror Porat ,  Assaf Weissman

IPC: H04N19/149 ,  H04N19/154 ,  H04N19/172

CPC classification number: H04N19/149 ,  H04N19/154 ,  H04N19/172

Abstract: A system includes a processing device to receive a video content, a quality metric, and a target bit rate for encoding the video content. The system includes encoding hardware to perform frame encoding on the video content and a controller coupled between the processing device and the encoding hardware. The controller is programmed with machine instructions to generate first QP values on a per-frame basis using a frame machine learning model with a first plurality of weights. The first plurality of weights depends at least in part on the quality metric and the target bit rate. The controller is further programmed to provide the first QP values to the encoding hardware for rate control of the frame encoding.